1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
| //===- PPCInstrVSX.td - The PowerPC VSX Extension --*- tablegen -*-===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
// This file describes the VSX extension to the PowerPC instruction set.
//
//===----------------------------------------------------------------------===//
// *********************************** NOTE ***********************************
// ** For POWER8 Little Endian, the VSX swap optimization relies on knowing **
// ** which VMX and VSX instructions are lane-sensitive and which are not. **
// ** A lane-sensitive instruction relies, implicitly or explicitly, on **
// ** whether lanes are numbered from left to right. An instruction like **
// ** VADDFP is not lane-sensitive, because each lane of the result vector **
// ** relies only on the corresponding lane of the source vectors. However, **
// ** an instruction like VMULESB is lane-sensitive, because "even" and **
// ** "odd" lanes are different for big-endian and little-endian numbering. **
// ** **
// ** When adding new VMX and VSX instructions, please consider whether they **
// ** are lane-sensitive. If so, they must be added to a switch statement **
// ** in PPCVSXSwapRemoval::gatherVectorInstructions(). **
// ****************************************************************************
def PPCRegVSRCAsmOperand : AsmOperandClass {
let Name = "RegVSRC"; let PredicateMethod = "isVSRegNumber";
}
def vsrc : RegisterOperand<VSRC> {
let ParserMatchClass = PPCRegVSRCAsmOperand;
}
def PPCRegVSFRCAsmOperand : AsmOperandClass {
let Name = "RegVSFRC"; let PredicateMethod = "isVSRegNumber";
}
def vsfrc : RegisterOperand<VSFRC> {
let ParserMatchClass = PPCRegVSFRCAsmOperand;
}
def PPCRegVSSRCAsmOperand : AsmOperandClass {
let Name = "RegVSSRC"; let PredicateMethod = "isVSRegNumber";
}
def vssrc : RegisterOperand<VSSRC> {
let ParserMatchClass = PPCRegVSSRCAsmOperand;
}
def PPCRegSPILLTOVSRRCAsmOperand : AsmOperandClass {
let Name = "RegSPILLTOVSRRC"; let PredicateMethod = "isVSRegNumber";
}
def spilltovsrrc : RegisterOperand<SPILLTOVSRRC> {
let ParserMatchClass = PPCRegSPILLTOVSRRCAsmOperand;
}
def SDT_PPCldvsxlh : SDTypeProfile<1, 1, [
SDTCisVT<0, v4f32>, SDTCisPtrTy<1>
]>;
def SDT_PPCfpexth : SDTypeProfile<1, 2, [
SDTCisVT<0, v2f64>, SDTCisVT<1, v4f32>, SDTCisPtrTy<2>
]>;
def SDT_PPCldsplat : SDTypeProfile<1, 1, [
SDTCisVec<0>, SDTCisPtrTy<1>
]>;
// Little-endian-specific nodes.
def SDT_PPClxvd2x : SDTypeProfile<1, 1, [
SDTCisVT<0, v2f64>, SDTCisPtrTy<1>
]>;
def SDT_PPCstxvd2x : SDTypeProfile<0, 2, [
SDTCisVT<0, v2f64>, SDTCisPtrTy<1>
]>;
def SDT_PPCxxswapd : SDTypeProfile<1, 1, [
SDTCisSameAs<0, 1>
]>;
def SDTVecConv : SDTypeProfile<1, 2, [
SDTCisVec<0>, SDTCisVec<1>, SDTCisPtrTy<2>
]>;
def SDTVabsd : SDTypeProfile<1, 3, [
SDTCisVec<0>, SDTCisSameAs<0, 1>, SDTCisSameAs<0, 2>, SDTCisVT<3, i32>
]>;
def SDT_PPCld_vec_be : SDTypeProfile<1, 1, [
SDTCisVec<0>, SDTCisPtrTy<1>
]>;
def SDT_PPCst_vec_be : SDTypeProfile<0, 2, [
SDTCisVec<0>, SDTCisPtrTy<1>
]>;
def PPClxvd2x : SDNode<"PPCISD::LXVD2X", SDT_PPClxvd2x,
[SDNPHasChain, SDNPMayLoad, SDNPMemOperand]>;
def PPCstxvd2x : SDNode<"PPCISD::STXVD2X", SDT_PPCstxvd2x,
[SDNPHasChain, SDNPMayStore]>;
def PPCld_vec_be : SDNode<"PPCISD::LOAD_VEC_BE", SDT_PPCld_vec_be,
[SDNPHasChain, SDNPMayLoad, SDNPMemOperand]>;
def PPCst_vec_be : SDNode<"PPCISD::STORE_VEC_BE", SDT_PPCst_vec_be,
[SDNPHasChain, SDNPMayStore]>;
def PPCxxswapd : SDNode<"PPCISD::XXSWAPD", SDT_PPCxxswapd, [SDNPHasChain]>;
def PPCmfvsr : SDNode<"PPCISD::MFVSR", SDTUnaryOp, []>;
def PPCmtvsra : SDNode<"PPCISD::MTVSRA", SDTUnaryOp, []>;
def PPCmtvsrz : SDNode<"PPCISD::MTVSRZ", SDTUnaryOp, []>;
def PPCsvec2fp : SDNode<"PPCISD::SINT_VEC_TO_FP", SDTVecConv, []>;
def PPCuvec2fp: SDNode<"PPCISD::UINT_VEC_TO_FP", SDTVecConv, []>;
def PPCswapNoChain : SDNode<"PPCISD::SWAP_NO_CHAIN", SDT_PPCxxswapd>;
def PPCvabsd : SDNode<"PPCISD::VABSD", SDTVabsd, []>;
def PPCfpexth : SDNode<"PPCISD::FP_EXTEND_HALF", SDT_PPCfpexth, []>;
def PPCldvsxlh : SDNode<"PPCISD::LD_VSX_LH", SDT_PPCldvsxlh,
[SDNPHasChain, SDNPMayLoad, SDNPMemOperand]>;
def PPCldsplat : SDNode<"PPCISD::LD_SPLAT", SDT_PPCldsplat,
[SDNPHasChain, SDNPMayLoad, SDNPMemOperand]>;
multiclass XX3Form_Rcr<bits<6> opcode, bits<7> xo, string asmbase,
string asmstr, InstrItinClass itin, Intrinsic Int,
ValueType OutTy, ValueType InTy> {
let BaseName = asmbase in {
def NAME : XX3Form_Rc<opcode, xo, (outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
!strconcat(asmbase, !strconcat(" ", asmstr)), itin,
[(set OutTy:$XT, (Int InTy:$XA, InTy:$XB))]>;
let Defs = [CR6] in
def o : XX3Form_Rc<opcode, xo, (outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
!strconcat(asmbase, !strconcat(". ", asmstr)), itin,
[(set InTy:$XT,
(InTy (PPCvcmp_o InTy:$XA, InTy:$XB, xo)))]>,
isDOT;
}
}
// Instruction form with a single input register for instructions such as
// XXPERMDI. The reason for defining this is that specifying multiple chained
// operands (such as loads) to an instruction will perform both chained
// operations rather than coalescing them into a single register - even though
// the source memory location is the same. This simply forces the instruction
// to use the same register for both inputs.
// For example, an output DAG such as this:
// (XXPERMDI (LXSIBZX xoaddr:$src), (LXSIBZX xoaddr:$src ), 0))
// would result in two load instructions emitted and used as separate inputs
// to the XXPERMDI instruction.
class XX3Form_2s<bits<6> opcode, bits<5> xo, dag OOL, dag IOL, string asmstr,
InstrItinClass itin, list<dag> pattern>
: XX3Form_2<opcode, xo, OOL, IOL, asmstr, itin, pattern> {
let XB = XA;
}
def HasVSX : Predicate<"PPCSubTarget->hasVSX()">;
def IsLittleEndian : Predicate<"PPCSubTarget->isLittleEndian()">;
def IsBigEndian : Predicate<"!PPCSubTarget->isLittleEndian()">;
def HasOnlySwappingMemOps : Predicate<"!PPCSubTarget->hasP9Vector()">;
let Predicates = [HasVSX] in {
let AddedComplexity = 400 in { // Prefer VSX patterns over non-VSX patterns.
let hasSideEffects = 0 in { // VSX instructions don't have side effects.
let Uses = [RM] in {
// Load indexed instructions
let mayLoad = 1, mayStore = 0 in {
let CodeSize = 3 in
def LXSDX : XX1Form_memOp<31, 588,
(outs vsfrc:$XT), (ins memrr:$src),
"lxsdx $XT, $src", IIC_LdStLFD,
[]>;
// Pseudo instruction XFLOADf64 will be expanded to LXSDX or LFDX later
let CodeSize = 3 in
def XFLOADf64 : PseudoXFormMemOp<(outs vsfrc:$XT), (ins memrr:$src),
"#XFLOADf64",
[(set f64:$XT, (load xoaddr:$src))]>;
let Predicates = [HasVSX, HasOnlySwappingMemOps] in
def LXVD2X : XX1Form_memOp<31, 844,
(outs vsrc:$XT), (ins memrr:$src),
"lxvd2x $XT, $src", IIC_LdStLFD,
[(set v2f64:$XT, (int_ppc_vsx_lxvd2x xoaddr:$src))]>;
def LXVDSX : XX1Form_memOp<31, 332,
(outs vsrc:$XT), (ins memrr:$src),
"lxvdsx $XT, $src", IIC_LdStLFD, []>;
let Predicates = [HasVSX, HasOnlySwappingMemOps] in
def LXVW4X : XX1Form_memOp<31, 780,
(outs vsrc:$XT), (ins memrr:$src),
"lxvw4x $XT, $src", IIC_LdStLFD,
[]>;
} // mayLoad
// Store indexed instructions
let mayStore = 1, mayLoad = 0 in {
let CodeSize = 3 in
def STXSDX : XX1Form_memOp<31, 716,
(outs), (ins vsfrc:$XT, memrr:$dst),
"stxsdx $XT, $dst", IIC_LdStSTFD,
[]>;
// Pseudo instruction XFSTOREf64 will be expanded to STXSDX or STFDX later
let CodeSize = 3 in
def XFSTOREf64 : PseudoXFormMemOp<(outs), (ins vsfrc:$XT, memrr:$dst),
"#XFSTOREf64",
[(store f64:$XT, xoaddr:$dst)]>;
let Predicates = [HasVSX, HasOnlySwappingMemOps] in {
// The behaviour of this instruction is endianness-specific so we provide no
// pattern to match it without considering endianness.
def STXVD2X : XX1Form_memOp<31, 972,
(outs), (ins vsrc:$XT, memrr:$dst),
"stxvd2x $XT, $dst", IIC_LdStSTFD,
[]>;
def STXVW4X : XX1Form_memOp<31, 908,
(outs), (ins vsrc:$XT, memrr:$dst),
"stxvw4x $XT, $dst", IIC_LdStSTFD,
[]>;
}
} // mayStore
// Add/Mul Instructions
let isCommutable = 1 in {
def XSADDDP : XX3Form<60, 32,
(outs vsfrc:$XT), (ins vsfrc:$XA, vsfrc:$XB),
"xsadddp $XT, $XA, $XB", IIC_VecFP,
[(set f64:$XT, (fadd f64:$XA, f64:$XB))]>;
def XSMULDP : XX3Form<60, 48,
(outs vsfrc:$XT), (ins vsfrc:$XA, vsfrc:$XB),
"xsmuldp $XT, $XA, $XB", IIC_VecFP,
[(set f64:$XT, (fmul f64:$XA, f64:$XB))]>;
def XVADDDP : XX3Form<60, 96,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xvadddp $XT, $XA, $XB", IIC_VecFP,
[(set v2f64:$XT, (fadd v2f64:$XA, v2f64:$XB))]>;
def XVADDSP : XX3Form<60, 64,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xvaddsp $XT, $XA, $XB", IIC_VecFP,
[(set v4f32:$XT, (fadd v4f32:$XA, v4f32:$XB))]>;
def XVMULDP : XX3Form<60, 112,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xvmuldp $XT, $XA, $XB", IIC_VecFP,
[(set v2f64:$XT, (fmul v2f64:$XA, v2f64:$XB))]>;
def XVMULSP : XX3Form<60, 80,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xvmulsp $XT, $XA, $XB", IIC_VecFP,
[(set v4f32:$XT, (fmul v4f32:$XA, v4f32:$XB))]>;
}
// Subtract Instructions
def XSSUBDP : XX3Form<60, 40,
(outs vsfrc:$XT), (ins vsfrc:$XA, vsfrc:$XB),
"xssubdp $XT, $XA, $XB", IIC_VecFP,
[(set f64:$XT, (fsub f64:$XA, f64:$XB))]>;
def XVSUBDP : XX3Form<60, 104,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xvsubdp $XT, $XA, $XB", IIC_VecFP,
[(set v2f64:$XT, (fsub v2f64:$XA, v2f64:$XB))]>;
def XVSUBSP : XX3Form<60, 72,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xvsubsp $XT, $XA, $XB", IIC_VecFP,
[(set v4f32:$XT, (fsub v4f32:$XA, v4f32:$XB))]>;
// FMA Instructions
let BaseName = "XSMADDADP" in {
let isCommutable = 1 in
def XSMADDADP : XX3Form<60, 33,
(outs vsfrc:$XT), (ins vsfrc:$XTi, vsfrc:$XA, vsfrc:$XB),
"xsmaddadp $XT, $XA, $XB", IIC_VecFP,
[(set f64:$XT, (fma f64:$XA, f64:$XB, f64:$XTi))]>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
let IsVSXFMAAlt = 1 in
def XSMADDMDP : XX3Form<60, 41,
(outs vsfrc:$XT), (ins vsfrc:$XTi, vsfrc:$XA, vsfrc:$XB),
"xsmaddmdp $XT, $XA, $XB", IIC_VecFP, []>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
}
let BaseName = "XSMSUBADP" in {
let isCommutable = 1 in
def XSMSUBADP : XX3Form<60, 49,
(outs vsfrc:$XT), (ins vsfrc:$XTi, vsfrc:$XA, vsfrc:$XB),
"xsmsubadp $XT, $XA, $XB", IIC_VecFP,
[(set f64:$XT, (fma f64:$XA, f64:$XB, (fneg f64:$XTi)))]>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
let IsVSXFMAAlt = 1 in
def XSMSUBMDP : XX3Form<60, 57,
(outs vsfrc:$XT), (ins vsfrc:$XTi, vsfrc:$XA, vsfrc:$XB),
"xsmsubmdp $XT, $XA, $XB", IIC_VecFP, []>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
}
let BaseName = "XSNMADDADP" in {
let isCommutable = 1 in
def XSNMADDADP : XX3Form<60, 161,
(outs vsfrc:$XT), (ins vsfrc:$XTi, vsfrc:$XA, vsfrc:$XB),
"xsnmaddadp $XT, $XA, $XB", IIC_VecFP,
[(set f64:$XT, (fneg (fma f64:$XA, f64:$XB, f64:$XTi)))]>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
let IsVSXFMAAlt = 1 in
def XSNMADDMDP : XX3Form<60, 169,
(outs vsfrc:$XT), (ins vsfrc:$XTi, vsfrc:$XA, vsfrc:$XB),
"xsnmaddmdp $XT, $XA, $XB", IIC_VecFP, []>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
}
let BaseName = "XSNMSUBADP" in {
let isCommutable = 1 in
def XSNMSUBADP : XX3Form<60, 177,
(outs vsfrc:$XT), (ins vsfrc:$XTi, vsfrc:$XA, vsfrc:$XB),
"xsnmsubadp $XT, $XA, $XB", IIC_VecFP,
[(set f64:$XT, (fneg (fma f64:$XA, f64:$XB, (fneg f64:$XTi))))]>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
let IsVSXFMAAlt = 1 in
def XSNMSUBMDP : XX3Form<60, 185,
(outs vsfrc:$XT), (ins vsfrc:$XTi, vsfrc:$XA, vsfrc:$XB),
"xsnmsubmdp $XT, $XA, $XB", IIC_VecFP, []>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
}
let BaseName = "XVMADDADP" in {
let isCommutable = 1 in
def XVMADDADP : XX3Form<60, 97,
(outs vsrc:$XT), (ins vsrc:$XTi, vsrc:$XA, vsrc:$XB),
"xvmaddadp $XT, $XA, $XB", IIC_VecFP,
[(set v2f64:$XT, (fma v2f64:$XA, v2f64:$XB, v2f64:$XTi))]>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
let IsVSXFMAAlt = 1 in
def XVMADDMDP : XX3Form<60, 105,
(outs vsrc:$XT), (ins vsrc:$XTi, vsrc:$XA, vsrc:$XB),
"xvmaddmdp $XT, $XA, $XB", IIC_VecFP, []>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
}
let BaseName = "XVMADDASP" in {
let isCommutable = 1 in
def XVMADDASP : XX3Form<60, 65,
(outs vsrc:$XT), (ins vsrc:$XTi, vsrc:$XA, vsrc:$XB),
"xvmaddasp $XT, $XA, $XB", IIC_VecFP,
[(set v4f32:$XT, (fma v4f32:$XA, v4f32:$XB, v4f32:$XTi))]>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
let IsVSXFMAAlt = 1 in
def XVMADDMSP : XX3Form<60, 73,
(outs vsrc:$XT), (ins vsrc:$XTi, vsrc:$XA, vsrc:$XB),
"xvmaddmsp $XT, $XA, $XB", IIC_VecFP, []>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
}
let BaseName = "XVMSUBADP" in {
let isCommutable = 1 in
def XVMSUBADP : XX3Form<60, 113,
(outs vsrc:$XT), (ins vsrc:$XTi, vsrc:$XA, vsrc:$XB),
"xvmsubadp $XT, $XA, $XB", IIC_VecFP,
[(set v2f64:$XT, (fma v2f64:$XA, v2f64:$XB, (fneg v2f64:$XTi)))]>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
let IsVSXFMAAlt = 1 in
def XVMSUBMDP : XX3Form<60, 121,
(outs vsrc:$XT), (ins vsrc:$XTi, vsrc:$XA, vsrc:$XB),
"xvmsubmdp $XT, $XA, $XB", IIC_VecFP, []>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
}
let BaseName = "XVMSUBASP" in {
let isCommutable = 1 in
def XVMSUBASP : XX3Form<60, 81,
(outs vsrc:$XT), (ins vsrc:$XTi, vsrc:$XA, vsrc:$XB),
"xvmsubasp $XT, $XA, $XB", IIC_VecFP,
[(set v4f32:$XT, (fma v4f32:$XA, v4f32:$XB, (fneg v4f32:$XTi)))]>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
let IsVSXFMAAlt = 1 in
def XVMSUBMSP : XX3Form<60, 89,
(outs vsrc:$XT), (ins vsrc:$XTi, vsrc:$XA, vsrc:$XB),
"xvmsubmsp $XT, $XA, $XB", IIC_VecFP, []>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
}
let BaseName = "XVNMADDADP" in {
let isCommutable = 1 in
def XVNMADDADP : XX3Form<60, 225,
(outs vsrc:$XT), (ins vsrc:$XTi, vsrc:$XA, vsrc:$XB),
"xvnmaddadp $XT, $XA, $XB", IIC_VecFP,
[(set v2f64:$XT, (fneg (fma v2f64:$XA, v2f64:$XB, v2f64:$XTi)))]>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
let IsVSXFMAAlt = 1 in
def XVNMADDMDP : XX3Form<60, 233,
(outs vsrc:$XT), (ins vsrc:$XTi, vsrc:$XA, vsrc:$XB),
"xvnmaddmdp $XT, $XA, $XB", IIC_VecFP, []>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
}
let BaseName = "XVNMADDASP" in {
let isCommutable = 1 in
def XVNMADDASP : XX3Form<60, 193,
(outs vsrc:$XT), (ins vsrc:$XTi, vsrc:$XA, vsrc:$XB),
"xvnmaddasp $XT, $XA, $XB", IIC_VecFP,
[(set v4f32:$XT, (fneg (fma v4f32:$XA, v4f32:$XB, v4f32:$XTi)))]>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
let IsVSXFMAAlt = 1 in
def XVNMADDMSP : XX3Form<60, 201,
(outs vsrc:$XT), (ins vsrc:$XTi, vsrc:$XA, vsrc:$XB),
"xvnmaddmsp $XT, $XA, $XB", IIC_VecFP, []>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
}
let BaseName = "XVNMSUBADP" in {
let isCommutable = 1 in
def XVNMSUBADP : XX3Form<60, 241,
(outs vsrc:$XT), (ins vsrc:$XTi, vsrc:$XA, vsrc:$XB),
"xvnmsubadp $XT, $XA, $XB", IIC_VecFP,
[(set v2f64:$XT, (fneg (fma v2f64:$XA, v2f64:$XB, (fneg v2f64:$XTi))))]>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
let IsVSXFMAAlt = 1 in
def XVNMSUBMDP : XX3Form<60, 249,
(outs vsrc:$XT), (ins vsrc:$XTi, vsrc:$XA, vsrc:$XB),
"xvnmsubmdp $XT, $XA, $XB", IIC_VecFP, []>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
}
let BaseName = "XVNMSUBASP" in {
let isCommutable = 1 in
def XVNMSUBASP : XX3Form<60, 209,
(outs vsrc:$XT), (ins vsrc:$XTi, vsrc:$XA, vsrc:$XB),
"xvnmsubasp $XT, $XA, $XB", IIC_VecFP,
[(set v4f32:$XT, (fneg (fma v4f32:$XA, v4f32:$XB, (fneg v4f32:$XTi))))]>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
let IsVSXFMAAlt = 1 in
def XVNMSUBMSP : XX3Form<60, 217,
(outs vsrc:$XT), (ins vsrc:$XTi, vsrc:$XA, vsrc:$XB),
"xvnmsubmsp $XT, $XA, $XB", IIC_VecFP, []>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
}
// Division Instructions
def XSDIVDP : XX3Form<60, 56,
(outs vsfrc:$XT), (ins vsfrc:$XA, vsfrc:$XB),
"xsdivdp $XT, $XA, $XB", IIC_FPDivD,
[(set f64:$XT, (fdiv f64:$XA, f64:$XB))]>;
def XSSQRTDP : XX2Form<60, 75,
(outs vsfrc:$XT), (ins vsfrc:$XB),
"xssqrtdp $XT, $XB", IIC_FPSqrtD,
[(set f64:$XT, (fsqrt f64:$XB))]>;
def XSREDP : XX2Form<60, 90,
(outs vsfrc:$XT), (ins vsfrc:$XB),
"xsredp $XT, $XB", IIC_VecFP,
[(set f64:$XT, (PPCfre f64:$XB))]>;
def XSRSQRTEDP : XX2Form<60, 74,
(outs vsfrc:$XT), (ins vsfrc:$XB),
"xsrsqrtedp $XT, $XB", IIC_VecFP,
[(set f64:$XT, (PPCfrsqrte f64:$XB))]>;
def XSTDIVDP : XX3Form_1<60, 61,
(outs crrc:$crD), (ins vsfrc:$XA, vsfrc:$XB),
"xstdivdp $crD, $XA, $XB", IIC_FPCompare, []>;
def XSTSQRTDP : XX2Form_1<60, 106,
(outs crrc:$crD), (ins vsfrc:$XB),
"xstsqrtdp $crD, $XB", IIC_FPCompare, []>;
def XVDIVDP : XX3Form<60, 120,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xvdivdp $XT, $XA, $XB", IIC_FPDivD,
[(set v2f64:$XT, (fdiv v2f64:$XA, v2f64:$XB))]>;
def XVDIVSP : XX3Form<60, 88,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xvdivsp $XT, $XA, $XB", IIC_FPDivS,
[(set v4f32:$XT, (fdiv v4f32:$XA, v4f32:$XB))]>;
def XVSQRTDP : XX2Form<60, 203,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvsqrtdp $XT, $XB", IIC_FPSqrtD,
[(set v2f64:$XT, (fsqrt v2f64:$XB))]>;
def XVSQRTSP : XX2Form<60, 139,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvsqrtsp $XT, $XB", IIC_FPSqrtS,
[(set v4f32:$XT, (fsqrt v4f32:$XB))]>;
def XVTDIVDP : XX3Form_1<60, 125,
(outs crrc:$crD), (ins vsrc:$XA, vsrc:$XB),
"xvtdivdp $crD, $XA, $XB", IIC_FPCompare, []>;
def XVTDIVSP : XX3Form_1<60, 93,
(outs crrc:$crD), (ins vsrc:$XA, vsrc:$XB),
"xvtdivsp $crD, $XA, $XB", IIC_FPCompare, []>;
def XVTSQRTDP : XX2Form_1<60, 234,
(outs crrc:$crD), (ins vsrc:$XB),
"xvtsqrtdp $crD, $XB", IIC_FPCompare, []>;
def XVTSQRTSP : XX2Form_1<60, 170,
(outs crrc:$crD), (ins vsrc:$XB),
"xvtsqrtsp $crD, $XB", IIC_FPCompare, []>;
def XVREDP : XX2Form<60, 218,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvredp $XT, $XB", IIC_VecFP,
[(set v2f64:$XT, (PPCfre v2f64:$XB))]>;
def XVRESP : XX2Form<60, 154,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvresp $XT, $XB", IIC_VecFP,
[(set v4f32:$XT, (PPCfre v4f32:$XB))]>;
def XVRSQRTEDP : XX2Form<60, 202,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvrsqrtedp $XT, $XB", IIC_VecFP,
[(set v2f64:$XT, (PPCfrsqrte v2f64:$XB))]>;
def XVRSQRTESP : XX2Form<60, 138,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvrsqrtesp $XT, $XB", IIC_VecFP,
[(set v4f32:$XT, (PPCfrsqrte v4f32:$XB))]>;
// Compare Instructions
def XSCMPODP : XX3Form_1<60, 43,
(outs crrc:$crD), (ins vsfrc:$XA, vsfrc:$XB),
"xscmpodp $crD, $XA, $XB", IIC_FPCompare, []>;
def XSCMPUDP : XX3Form_1<60, 35,
(outs crrc:$crD), (ins vsfrc:$XA, vsfrc:$XB),
"xscmpudp $crD, $XA, $XB", IIC_FPCompare, []>;
defm XVCMPEQDP : XX3Form_Rcr<60, 99,
"xvcmpeqdp", "$XT, $XA, $XB", IIC_VecFPCompare,
int_ppc_vsx_xvcmpeqdp, v2i64, v2f64>;
defm XVCMPEQSP : XX3Form_Rcr<60, 67,
"xvcmpeqsp", "$XT, $XA, $XB", IIC_VecFPCompare,
int_ppc_vsx_xvcmpeqsp, v4i32, v4f32>;
defm XVCMPGEDP : XX3Form_Rcr<60, 115,
"xvcmpgedp", "$XT, $XA, $XB", IIC_VecFPCompare,
int_ppc_vsx_xvcmpgedp, v2i64, v2f64>;
defm XVCMPGESP : XX3Form_Rcr<60, 83,
"xvcmpgesp", "$XT, $XA, $XB", IIC_VecFPCompare,
int_ppc_vsx_xvcmpgesp, v4i32, v4f32>;
defm XVCMPGTDP : XX3Form_Rcr<60, 107,
"xvcmpgtdp", "$XT, $XA, $XB", IIC_VecFPCompare,
int_ppc_vsx_xvcmpgtdp, v2i64, v2f64>;
defm XVCMPGTSP : XX3Form_Rcr<60, 75,
"xvcmpgtsp", "$XT, $XA, $XB", IIC_VecFPCompare,
int_ppc_vsx_xvcmpgtsp, v4i32, v4f32>;
// Move Instructions
def XSABSDP : XX2Form<60, 345,
(outs vsfrc:$XT), (ins vsfrc:$XB),
"xsabsdp $XT, $XB", IIC_VecFP,
[(set f64:$XT, (fabs f64:$XB))]>;
def XSNABSDP : XX2Form<60, 361,
(outs vsfrc:$XT), (ins vsfrc:$XB),
"xsnabsdp $XT, $XB", IIC_VecFP,
[(set f64:$XT, (fneg (fabs f64:$XB)))]>;
def XSNEGDP : XX2Form<60, 377,
(outs vsfrc:$XT), (ins vsfrc:$XB),
"xsnegdp $XT, $XB", IIC_VecFP,
[(set f64:$XT, (fneg f64:$XB))]>;
def XSCPSGNDP : XX3Form<60, 176,
(outs vsfrc:$XT), (ins vsfrc:$XA, vsfrc:$XB),
"xscpsgndp $XT, $XA, $XB", IIC_VecFP,
[(set f64:$XT, (fcopysign f64:$XB, f64:$XA))]>;
def XVABSDP : XX2Form<60, 473,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvabsdp $XT, $XB", IIC_VecFP,
[(set v2f64:$XT, (fabs v2f64:$XB))]>;
def XVABSSP : XX2Form<60, 409,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvabssp $XT, $XB", IIC_VecFP,
[(set v4f32:$XT, (fabs v4f32:$XB))]>;
def XVCPSGNDP : XX3Form<60, 240,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xvcpsgndp $XT, $XA, $XB", IIC_VecFP,
[(set v2f64:$XT, (fcopysign v2f64:$XB, v2f64:$XA))]>;
def XVCPSGNSP : XX3Form<60, 208,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xvcpsgnsp $XT, $XA, $XB", IIC_VecFP,
[(set v4f32:$XT, (fcopysign v4f32:$XB, v4f32:$XA))]>;
def XVNABSDP : XX2Form<60, 489,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvnabsdp $XT, $XB", IIC_VecFP,
[(set v2f64:$XT, (fneg (fabs v2f64:$XB)))]>;
def XVNABSSP : XX2Form<60, 425,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvnabssp $XT, $XB", IIC_VecFP,
[(set v4f32:$XT, (fneg (fabs v4f32:$XB)))]>;
def XVNEGDP : XX2Form<60, 505,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvnegdp $XT, $XB", IIC_VecFP,
[(set v2f64:$XT, (fneg v2f64:$XB))]>;
def XVNEGSP : XX2Form<60, 441,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvnegsp $XT, $XB", IIC_VecFP,
[(set v4f32:$XT, (fneg v4f32:$XB))]>;
// Conversion Instructions
def XSCVDPSP : XX2Form<60, 265,
(outs vsfrc:$XT), (ins vsfrc:$XB),
"xscvdpsp $XT, $XB", IIC_VecFP, []>;
def XSCVDPSXDS : XX2Form<60, 344,
(outs vsfrc:$XT), (ins vsfrc:$XB),
"xscvdpsxds $XT, $XB", IIC_VecFP,
[(set f64:$XT, (PPCfctidz f64:$XB))]>;
let isCodeGenOnly = 1 in
def XSCVDPSXDSs : XX2Form<60, 344,
(outs vssrc:$XT), (ins vssrc:$XB),
"xscvdpsxds $XT, $XB", IIC_VecFP,
[(set f32:$XT, (PPCfctidz f32:$XB))]>;
def XSCVDPSXWS : XX2Form<60, 88,
(outs vsfrc:$XT), (ins vsfrc:$XB),
"xscvdpsxws $XT, $XB", IIC_VecFP,
[(set f64:$XT, (PPCfctiwz f64:$XB))]>;
let isCodeGenOnly = 1 in
def XSCVDPSXWSs : XX2Form<60, 88,
(outs vssrc:$XT), (ins vssrc:$XB),
"xscvdpsxws $XT, $XB", IIC_VecFP,
[(set f32:$XT, (PPCfctiwz f32:$XB))]>;
def XSCVDPUXDS : XX2Form<60, 328,
(outs vsfrc:$XT), (ins vsfrc:$XB),
"xscvdpuxds $XT, $XB", IIC_VecFP,
[(set f64:$XT, (PPCfctiduz f64:$XB))]>;
let isCodeGenOnly = 1 in
def XSCVDPUXDSs : XX2Form<60, 328,
(outs vssrc:$XT), (ins vssrc:$XB),
"xscvdpuxds $XT, $XB", IIC_VecFP,
[(set f32:$XT, (PPCfctiduz f32:$XB))]>;
def XSCVDPUXWS : XX2Form<60, 72,
(outs vsfrc:$XT), (ins vsfrc:$XB),
"xscvdpuxws $XT, $XB", IIC_VecFP,
[(set f64:$XT, (PPCfctiwuz f64:$XB))]>;
let isCodeGenOnly = 1 in
def XSCVDPUXWSs : XX2Form<60, 72,
(outs vssrc:$XT), (ins vssrc:$XB),
"xscvdpuxws $XT, $XB", IIC_VecFP,
[(set f32:$XT, (PPCfctiwuz f32:$XB))]>;
def XSCVSPDP : XX2Form<60, 329,
(outs vsfrc:$XT), (ins vsfrc:$XB),
"xscvspdp $XT, $XB", IIC_VecFP, []>;
def XSCVSXDDP : XX2Form<60, 376,
(outs vsfrc:$XT), (ins vsfrc:$XB),
"xscvsxddp $XT, $XB", IIC_VecFP,
[(set f64:$XT, (PPCfcfid f64:$XB))]>;
def XSCVUXDDP : XX2Form<60, 360,
(outs vsfrc:$XT), (ins vsfrc:$XB),
"xscvuxddp $XT, $XB", IIC_VecFP,
[(set f64:$XT, (PPCfcfidu f64:$XB))]>;
def XVCVDPSP : XX2Form<60, 393,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvcvdpsp $XT, $XB", IIC_VecFP,
[(set v4f32:$XT, (int_ppc_vsx_xvcvdpsp v2f64:$XB))]>;
def XVCVDPSXDS : XX2Form<60, 472,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvcvdpsxds $XT, $XB", IIC_VecFP,
[(set v2i64:$XT, (fp_to_sint v2f64:$XB))]>;
def XVCVDPSXWS : XX2Form<60, 216,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvcvdpsxws $XT, $XB", IIC_VecFP,
[(set v4i32:$XT, (int_ppc_vsx_xvcvdpsxws v2f64:$XB))]>;
def XVCVDPUXDS : XX2Form<60, 456,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvcvdpuxds $XT, $XB", IIC_VecFP,
[(set v2i64:$XT, (fp_to_uint v2f64:$XB))]>;
def XVCVDPUXWS : XX2Form<60, 200,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvcvdpuxws $XT, $XB", IIC_VecFP,
[(set v4i32:$XT, (int_ppc_vsx_xvcvdpuxws v2f64:$XB))]>;
def XVCVSPDP : XX2Form<60, 457,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvcvspdp $XT, $XB", IIC_VecFP,
[(set v2f64:$XT, (int_ppc_vsx_xvcvspdp v4f32:$XB))]>;
def XVCVSPSXDS : XX2Form<60, 408,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvcvspsxds $XT, $XB", IIC_VecFP, []>;
def XVCVSPSXWS : XX2Form<60, 152,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvcvspsxws $XT, $XB", IIC_VecFP,
[(set v4i32:$XT, (fp_to_sint v4f32:$XB))]>;
def XVCVSPUXDS : XX2Form<60, 392,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvcvspuxds $XT, $XB", IIC_VecFP, []>;
def XVCVSPUXWS : XX2Form<60, 136,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvcvspuxws $XT, $XB", IIC_VecFP,
[(set v4i32:$XT, (fp_to_uint v4f32:$XB))]>;
def XVCVSXDDP : XX2Form<60, 504,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvcvsxddp $XT, $XB", IIC_VecFP,
[(set v2f64:$XT, (sint_to_fp v2i64:$XB))]>;
def XVCVSXDSP : XX2Form<60, 440,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvcvsxdsp $XT, $XB", IIC_VecFP,
[(set v4f32:$XT, (int_ppc_vsx_xvcvsxdsp v2i64:$XB))]>;
def XVCVSXWDP : XX2Form<60, 248,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvcvsxwdp $XT, $XB", IIC_VecFP,
[(set v2f64:$XT, (int_ppc_vsx_xvcvsxwdp v4i32:$XB))]>;
def XVCVSXWSP : XX2Form<60, 184,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvcvsxwsp $XT, $XB", IIC_VecFP,
[(set v4f32:$XT, (sint_to_fp v4i32:$XB))]>;
def XVCVUXDDP : XX2Form<60, 488,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvcvuxddp $XT, $XB", IIC_VecFP,
[(set v2f64:$XT, (uint_to_fp v2i64:$XB))]>;
def XVCVUXDSP : XX2Form<60, 424,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvcvuxdsp $XT, $XB", IIC_VecFP,
[(set v4f32:$XT, (int_ppc_vsx_xvcvuxdsp v2i64:$XB))]>;
def XVCVUXWDP : XX2Form<60, 232,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvcvuxwdp $XT, $XB", IIC_VecFP,
[(set v2f64:$XT, (int_ppc_vsx_xvcvuxwdp v4i32:$XB))]>;
def XVCVUXWSP : XX2Form<60, 168,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvcvuxwsp $XT, $XB", IIC_VecFP,
[(set v4f32:$XT, (uint_to_fp v4i32:$XB))]>;
// Rounding Instructions
def XSRDPI : XX2Form<60, 73,
(outs vsfrc:$XT), (ins vsfrc:$XB),
"xsrdpi $XT, $XB", IIC_VecFP,
[(set f64:$XT, (fround f64:$XB))]>;
def XSRDPIC : XX2Form<60, 107,
(outs vsfrc:$XT), (ins vsfrc:$XB),
"xsrdpic $XT, $XB", IIC_VecFP,
[(set f64:$XT, (fnearbyint f64:$XB))]>;
def XSRDPIM : XX2Form<60, 121,
(outs vsfrc:$XT), (ins vsfrc:$XB),
"xsrdpim $XT, $XB", IIC_VecFP,
[(set f64:$XT, (ffloor f64:$XB))]>;
def XSRDPIP : XX2Form<60, 105,
(outs vsfrc:$XT), (ins vsfrc:$XB),
"xsrdpip $XT, $XB", IIC_VecFP,
[(set f64:$XT, (fceil f64:$XB))]>;
def XSRDPIZ : XX2Form<60, 89,
(outs vsfrc:$XT), (ins vsfrc:$XB),
"xsrdpiz $XT, $XB", IIC_VecFP,
[(set f64:$XT, (ftrunc f64:$XB))]>;
def XVRDPI : XX2Form<60, 201,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvrdpi $XT, $XB", IIC_VecFP,
[(set v2f64:$XT, (fround v2f64:$XB))]>;
def XVRDPIC : XX2Form<60, 235,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvrdpic $XT, $XB", IIC_VecFP,
[(set v2f64:$XT, (fnearbyint v2f64:$XB))]>;
def XVRDPIM : XX2Form<60, 249,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvrdpim $XT, $XB", IIC_VecFP,
[(set v2f64:$XT, (ffloor v2f64:$XB))]>;
def XVRDPIP : XX2Form<60, 233,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvrdpip $XT, $XB", IIC_VecFP,
[(set v2f64:$XT, (fceil v2f64:$XB))]>;
def XVRDPIZ : XX2Form<60, 217,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvrdpiz $XT, $XB", IIC_VecFP,
[(set v2f64:$XT, (ftrunc v2f64:$XB))]>;
def XVRSPI : XX2Form<60, 137,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvrspi $XT, $XB", IIC_VecFP,
[(set v4f32:$XT, (fround v4f32:$XB))]>;
def XVRSPIC : XX2Form<60, 171,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvrspic $XT, $XB", IIC_VecFP,
[(set v4f32:$XT, (fnearbyint v4f32:$XB))]>;
def XVRSPIM : XX2Form<60, 185,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvrspim $XT, $XB", IIC_VecFP,
[(set v4f32:$XT, (ffloor v4f32:$XB))]>;
def XVRSPIP : XX2Form<60, 169,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvrspip $XT, $XB", IIC_VecFP,
[(set v4f32:$XT, (fceil v4f32:$XB))]>;
def XVRSPIZ : XX2Form<60, 153,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvrspiz $XT, $XB", IIC_VecFP,
[(set v4f32:$XT, (ftrunc v4f32:$XB))]>;
// Max/Min Instructions
let isCommutable = 1 in {
def XSMAXDP : XX3Form<60, 160,
(outs vsfrc:$XT), (ins vsfrc:$XA, vsfrc:$XB),
"xsmaxdp $XT, $XA, $XB", IIC_VecFP,
[(set vsfrc:$XT,
(int_ppc_vsx_xsmaxdp vsfrc:$XA, vsfrc:$XB))]>;
def XSMINDP : XX3Form<60, 168,
(outs vsfrc:$XT), (ins vsfrc:$XA, vsfrc:$XB),
"xsmindp $XT, $XA, $XB", IIC_VecFP,
[(set vsfrc:$XT,
(int_ppc_vsx_xsmindp vsfrc:$XA, vsfrc:$XB))]>;
def XVMAXDP : XX3Form<60, 224,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xvmaxdp $XT, $XA, $XB", IIC_VecFP,
[(set vsrc:$XT,
(int_ppc_vsx_xvmaxdp vsrc:$XA, vsrc:$XB))]>;
def XVMINDP : XX3Form<60, 232,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xvmindp $XT, $XA, $XB", IIC_VecFP,
[(set vsrc:$XT,
(int_ppc_vsx_xvmindp vsrc:$XA, vsrc:$XB))]>;
def XVMAXSP : XX3Form<60, 192,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xvmaxsp $XT, $XA, $XB", IIC_VecFP,
[(set vsrc:$XT,
(int_ppc_vsx_xvmaxsp vsrc:$XA, vsrc:$XB))]>;
def XVMINSP : XX3Form<60, 200,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xvminsp $XT, $XA, $XB", IIC_VecFP,
[(set vsrc:$XT,
(int_ppc_vsx_xvminsp vsrc:$XA, vsrc:$XB))]>;
} // isCommutable
} // Uses = [RM]
// Logical Instructions
let isCommutable = 1 in
def XXLAND : XX3Form<60, 130,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xxland $XT, $XA, $XB", IIC_VecGeneral,
[(set v4i32:$XT, (and v4i32:$XA, v4i32:$XB))]>;
def XXLANDC : XX3Form<60, 138,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xxlandc $XT, $XA, $XB", IIC_VecGeneral,
[(set v4i32:$XT, (and v4i32:$XA,
(vnot_ppc v4i32:$XB)))]>;
let isCommutable = 1 in {
def XXLNOR : XX3Form<60, 162,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xxlnor $XT, $XA, $XB", IIC_VecGeneral,
[(set v4i32:$XT, (vnot_ppc (or v4i32:$XA,
v4i32:$XB)))]>;
def XXLOR : XX3Form<60, 146,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xxlor $XT, $XA, $XB", IIC_VecGeneral,
[(set v4i32:$XT, (or v4i32:$XA, v4i32:$XB))]>;
let isCodeGenOnly = 1 in
def XXLORf: XX3Form<60, 146,
(outs vsfrc:$XT), (ins vsfrc:$XA, vsfrc:$XB),
"xxlor $XT, $XA, $XB", IIC_VecGeneral, []>;
def XXLXOR : XX3Form<60, 154,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xxlxor $XT, $XA, $XB", IIC_VecGeneral,
[(set v4i32:$XT, (xor v4i32:$XA, v4i32:$XB))]>;
} // isCommutable
let isCodeGenOnly = 1, isMoveImm = 1, isAsCheapAsAMove = 1,
isReMaterializable = 1 in {
def XXLXORz : XX3Form_SameOp<60, 154, (outs vsrc:$XT), (ins),
"xxlxor $XT, $XT, $XT", IIC_VecGeneral,
[(set v4i32:$XT, (v4i32 immAllZerosV))]>;
def XXLXORdpz : XX3Form_SameOp<60, 154,
(outs vsfrc:$XT), (ins),
"xxlxor $XT, $XT, $XT", IIC_VecGeneral,
[(set f64:$XT, (fpimm0))]>;
def XXLXORspz : XX3Form_SameOp<60, 154,
(outs vssrc:$XT), (ins),
"xxlxor $XT, $XT, $XT", IIC_VecGeneral,
[(set f32:$XT, (fpimm0))]>;
}
// Permutation Instructions
def XXMRGHW : XX3Form<60, 18,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xxmrghw $XT, $XA, $XB", IIC_VecPerm, []>;
def XXMRGLW : XX3Form<60, 50,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xxmrglw $XT, $XA, $XB", IIC_VecPerm, []>;
def XXPERMDI : XX3Form_2<60, 10,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB, u2imm:$DM),
"xxpermdi $XT, $XA, $XB, $DM", IIC_VecPerm,
[(set v2i64:$XT, (PPCxxpermdi v2i64:$XA, v2i64:$XB,
imm32SExt16:$DM))]>;
let isCodeGenOnly = 1 in
def XXPERMDIs : XX3Form_2s<60, 10, (outs vsrc:$XT), (ins vsfrc:$XA, u2imm:$DM),
"xxpermdi $XT, $XA, $XA, $DM", IIC_VecPerm, []>;
def XXSEL : XX4Form<60, 3,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB, vsrc:$XC),
"xxsel $XT, $XA, $XB, $XC", IIC_VecPerm, []>;
def XXSLDWI : XX3Form_2<60, 2,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB, u2imm:$SHW),
"xxsldwi $XT, $XA, $XB, $SHW", IIC_VecPerm,
[(set v4i32:$XT, (PPCvecshl v4i32:$XA, v4i32:$XB,
imm32SExt16:$SHW))]>;
let isCodeGenOnly = 1 in
def XXSLDWIs : XX3Form_2s<60, 2,
(outs vsrc:$XT), (ins vsfrc:$XA, u2imm:$SHW),
"xxsldwi $XT, $XA, $XA, $SHW", IIC_VecPerm, []>;
def XXSPLTW : XX2Form_2<60, 164,
(outs vsrc:$XT), (ins vsrc:$XB, u2imm:$UIM),
"xxspltw $XT, $XB, $UIM", IIC_VecPerm,
[(set v4i32:$XT,
(PPCxxsplt v4i32:$XB, imm32SExt16:$UIM))]>;
let isCodeGenOnly = 1 in
def XXSPLTWs : XX2Form_2<60, 164,
(outs vsrc:$XT), (ins vsfrc:$XB, u2imm:$UIM),
"xxspltw $XT, $XB, $UIM", IIC_VecPerm, []>;
} // hasSideEffects
// SELECT_CC_* - Used to implement the SELECT_CC DAG operation. Expanded after
// instruction selection into a branch sequence.
let PPC970_Single = 1 in {
def SELECT_CC_VSRC: PPCCustomInserterPseudo<(outs vsrc:$dst),
(ins crrc:$cond, vsrc:$T, vsrc:$F, i32imm:$BROPC),
"#SELECT_CC_VSRC",
[]>;
def SELECT_VSRC: PPCCustomInserterPseudo<(outs vsrc:$dst),
(ins crbitrc:$cond, vsrc:$T, vsrc:$F),
"#SELECT_VSRC",
[(set v2f64:$dst,
(select i1:$cond, v2f64:$T, v2f64:$F))]>;
def SELECT_CC_VSFRC: PPCCustomInserterPseudo<(outs f8rc:$dst),
(ins crrc:$cond, f8rc:$T, f8rc:$F,
i32imm:$BROPC), "#SELECT_CC_VSFRC",
[]>;
def SELECT_VSFRC: PPCCustomInserterPseudo<(outs f8rc:$dst),
(ins crbitrc:$cond, f8rc:$T, f8rc:$F),
"#SELECT_VSFRC",
[(set f64:$dst,
(select i1:$cond, f64:$T, f64:$F))]>;
def SELECT_CC_VSSRC: PPCCustomInserterPseudo<(outs f4rc:$dst),
(ins crrc:$cond, f4rc:$T, f4rc:$F,
i32imm:$BROPC), "#SELECT_CC_VSSRC",
[]>;
def SELECT_VSSRC: PPCCustomInserterPseudo<(outs f4rc:$dst),
(ins crbitrc:$cond, f4rc:$T, f4rc:$F),
"#SELECT_VSSRC",
[(set f32:$dst,
(select i1:$cond, f32:$T, f32:$F))]>;
}
} // AddedComplexity
def : InstAlias<"xvmovdp $XT, $XB",
(XVCPSGNDP vsrc:$XT, vsrc:$XB, vsrc:$XB)>;
def : InstAlias<"xvmovsp $XT, $XB",
(XVCPSGNSP vsrc:$XT, vsrc:$XB, vsrc:$XB)>;
def : InstAlias<"xxspltd $XT, $XB, 0",
(XXPERMDI vsrc:$XT, vsrc:$XB, vsrc:$XB, 0)>;
def : InstAlias<"xxspltd $XT, $XB, 1",
(XXPERMDI vsrc:$XT, vsrc:$XB, vsrc:$XB, 3)>;
def : InstAlias<"xxmrghd $XT, $XA, $XB",
(XXPERMDI vsrc:$XT, vsrc:$XA, vsrc:$XB, 0)>;
def : InstAlias<"xxmrgld $XT, $XA, $XB",
(XXPERMDI vsrc:$XT, vsrc:$XA, vsrc:$XB, 3)>;
def : InstAlias<"xxswapd $XT, $XB",
(XXPERMDI vsrc:$XT, vsrc:$XB, vsrc:$XB, 2)>;
def : InstAlias<"xxspltd $XT, $XB, 0",
(XXPERMDIs vsrc:$XT, vsfrc:$XB, 0)>;
def : InstAlias<"xxspltd $XT, $XB, 1",
(XXPERMDIs vsrc:$XT, vsfrc:$XB, 3)>;
def : InstAlias<"xxswapd $XT, $XB",
(XXPERMDIs vsrc:$XT, vsfrc:$XB, 2)>;
let AddedComplexity = 400 in { // Prefer VSX patterns over non-VSX patterns.
def : Pat<(v4i32 (vnot_ppc v4i32:$A)),
(v4i32 (XXLNOR $A, $A))>;
def : Pat<(v4i32 (or (and (vnot_ppc v4i32:$C), v4i32:$A),
(and v4i32:$B, v4i32:$C))),
(v4i32 (XXSEL $A, $B, $C))>;
let Predicates = [IsBigEndian] in {
def : Pat<(v2f64 (scalar_to_vector f64:$A)),
(v2f64 (SUBREG_TO_REG (i64 1), $A, sub_64))>;
def : Pat<(f64 (extractelt v2f64:$S, 0)),
(f64 (EXTRACT_SUBREG $S, sub_64))>;
def : Pat<(f64 (extractelt v2f64:$S, 1)),
(f64 (EXTRACT_SUBREG (XXPERMDI $S, $S, 2), sub_64))>;
}
let Predicates = [IsLittleEndian] in {
def : Pat<(v2f64 (scalar_to_vector f64:$A)),
(v2f64 (XXPERMDI (SUBREG_TO_REG (i64 1), $A, sub_64),
(SUBREG_TO_REG (i64 1), $A, sub_64), 0))>;
def : Pat<(f64 (extractelt v2f64:$S, 0)),
(f64 (EXTRACT_SUBREG (XXPERMDI $S, $S, 2), sub_64))>;
def : Pat<(f64 (extractelt v2f64:$S, 1)),
(f64 (EXTRACT_SUBREG $S, sub_64))>;
}
// Additional fnmsub patterns: -a*b + c == -(a*b - c)
def : Pat<(fma (fneg f64:$A), f64:$B, f64:$C),
(XSNMSUBADP $C, $A, $B)>;
def : Pat<(fma f64:$A, (fneg f64:$B), f64:$C),
(XSNMSUBADP $C, $A, $B)>;
def : Pat<(fma (fneg v2f64:$A), v2f64:$B, v2f64:$C),
(XVNMSUBADP $C, $A, $B)>;
def : Pat<(fma v2f64:$A, (fneg v2f64:$B), v2f64:$C),
(XVNMSUBADP $C, $A, $B)>;
def : Pat<(fma (fneg v4f32:$A), v4f32:$B, v4f32:$C),
(XVNMSUBASP $C, $A, $B)>;
def : Pat<(fma v4f32:$A, (fneg v4f32:$B), v4f32:$C),
(XVNMSUBASP $C, $A, $B)>;
def : Pat<(v2f64 (bitconvert v4f32:$A)),
(COPY_TO_REGCLASS $A, VSRC)>;
def : Pat<(v2f64 (bitconvert v4i32:$A)),
(COPY_TO_REGCLASS $A, VSRC)>;
def : Pat<(v2f64 (bitconvert v8i16:$A)),
(COPY_TO_REGCLASS $A, VSRC)>;
def : Pat<(v2f64 (bitconvert v16i8:$A)),
(COPY_TO_REGCLASS $A, VSRC)>;
def : Pat<(v4f32 (bitconvert v2f64:$A)),
(COPY_TO_REGCLASS $A, VRRC)>;
def : Pat<(v4i32 (bitconvert v2f64:$A)),
(COPY_TO_REGCLASS $A, VRRC)>;
def : Pat<(v8i16 (bitconvert v2f64:$A)),
(COPY_TO_REGCLASS $A, VRRC)>;
def : Pat<(v16i8 (bitconvert v2f64:$A)),
(COPY_TO_REGCLASS $A, VRRC)>;
def : Pat<(v2i64 (bitconvert v4f32:$A)),
(COPY_TO_REGCLASS $A, VSRC)>;
def : Pat<(v2i64 (bitconvert v4i32:$A)),
(COPY_TO_REGCLASS $A, VSRC)>;
def : Pat<(v2i64 (bitconvert v8i16:$A)),
(COPY_TO_REGCLASS $A, VSRC)>;
def : Pat<(v2i64 (bitconvert v16i8:$A)),
(COPY_TO_REGCLASS $A, VSRC)>;
def : Pat<(v4f32 (bitconvert v2i64:$A)),
(COPY_TO_REGCLASS $A, VRRC)>;
def : Pat<(v4i32 (bitconvert v2i64:$A)),
(COPY_TO_REGCLASS $A, VRRC)>;
def : Pat<(v8i16 (bitconvert v2i64:$A)),
(COPY_TO_REGCLASS $A, VRRC)>;
def : Pat<(v16i8 (bitconvert v2i64:$A)),
(COPY_TO_REGCLASS $A, VRRC)>;
def : Pat<(v2f64 (bitconvert v2i64:$A)),
(COPY_TO_REGCLASS $A, VRRC)>;
def : Pat<(v2i64 (bitconvert v2f64:$A)),
(COPY_TO_REGCLASS $A, VRRC)>;
def : Pat<(v2f64 (bitconvert v1i128:$A)),
(COPY_TO_REGCLASS $A, VRRC)>;
def : Pat<(v1i128 (bitconvert v2f64:$A)),
(COPY_TO_REGCLASS $A, VRRC)>;
def : Pat<(v2i64 (bitconvert f128:$A)),
(COPY_TO_REGCLASS $A, VRRC)>;
def : Pat<(v4i32 (bitconvert f128:$A)),
(COPY_TO_REGCLASS $A, VRRC)>;
def : Pat<(v8i16 (bitconvert f128:$A)),
(COPY_TO_REGCLASS $A, VRRC)>;
def : Pat<(v16i8 (bitconvert f128:$A)),
(COPY_TO_REGCLASS $A, VRRC)>;
def : Pat<(v2f64 (PPCsvec2fp v4i32:$C, 0)),
(v2f64 (XVCVSXWDP (v2i64 (XXMRGHW $C, $C))))>;
def : Pat<(v2f64 (PPCsvec2fp v4i32:$C, 1)),
(v2f64 (XVCVSXWDP (v2i64 (XXMRGLW $C, $C))))>;
def : Pat<(v2f64 (PPCuvec2fp v4i32:$C, 0)),
(v2f64 (XVCVUXWDP (v2i64 (XXMRGHW $C, $C))))>;
def : Pat<(v2f64 (PPCuvec2fp v4i32:$C, 1)),
(v2f64 (XVCVUXWDP (v2i64 (XXMRGLW $C, $C))))>;
def : Pat<(v2f64 (PPCfpexth v4f32:$C, 0)), (XVCVSPDP (XXMRGHW $C, $C))>;
def : Pat<(v2f64 (PPCfpexth v4f32:$C, 1)), (XVCVSPDP (XXMRGLW $C, $C))>;
// Loads.
let Predicates = [HasVSX, HasOnlySwappingMemOps] in {
def : Pat<(v2f64 (PPClxvd2x xoaddr:$src)), (LXVD2X xoaddr:$src)>;
// Stores.
def : Pat<(int_ppc_vsx_stxvd2x v2f64:$rS, xoaddr:$dst),
(STXVD2X $rS, xoaddr:$dst)>;
def : Pat<(PPCstxvd2x v2f64:$rS, xoaddr:$dst), (STXVD2X $rS, xoaddr:$dst)>;
}
// Load vector big endian order
let Predicates = [IsLittleEndian, HasVSX] in {
def : Pat<(v2f64 (PPCld_vec_be xoaddr:$src)), (LXVD2X xoaddr:$src)>;
def : Pat<(PPCst_vec_be v2f64:$rS, xoaddr:$dst), (STXVD2X $rS, xoaddr:$dst)>;
def : Pat<(v4f32 (PPCld_vec_be xoaddr:$src)), (LXVW4X xoaddr:$src)>;
def : Pat<(PPCst_vec_be v4f32:$rS, xoaddr:$dst), (STXVW4X $rS, xoaddr:$dst)>;
def : Pat<(v2i64 (PPCld_vec_be xoaddr:$src)), (LXVD2X xoaddr:$src)>;
def : Pat<(PPCst_vec_be v2i64:$rS, xoaddr:$dst), (STXVD2X $rS, xoaddr:$dst)>;
def : Pat<(v4i32 (PPCld_vec_be xoaddr:$src)), (LXVW4X xoaddr:$src)>;
def : Pat<(PPCst_vec_be v4i32:$rS, xoaddr:$dst), (STXVW4X $rS, xoaddr:$dst)>;
}
let Predicates = [IsBigEndian, HasVSX, HasOnlySwappingMemOps] in {
def : Pat<(v2f64 (load xoaddr:$src)), (LXVD2X xoaddr:$src)>;
def : Pat<(v2i64 (load xoaddr:$src)), (LXVD2X xoaddr:$src)>;
def : Pat<(v4i32 (load xoaddr:$src)), (LXVW4X xoaddr:$src)>;
def : Pat<(v4i32 (int_ppc_vsx_lxvw4x xoaddr:$src)), (LXVW4X xoaddr:$src)>;
def : Pat<(store v2f64:$rS, xoaddr:$dst), (STXVD2X $rS, xoaddr:$dst)>;
def : Pat<(store v2i64:$rS, xoaddr:$dst), (STXVD2X $rS, xoaddr:$dst)>;
def : Pat<(store v4i32:$XT, xoaddr:$dst), (STXVW4X $XT, xoaddr:$dst)>;
def : Pat<(int_ppc_vsx_stxvw4x v4i32:$rS, xoaddr:$dst),
(STXVW4X $rS, xoaddr:$dst)>;
}
// Permutes.
def : Pat<(v2f64 (PPCxxswapd v2f64:$src)), (XXPERMDI $src, $src, 2)>;
def : Pat<(v2i64 (PPCxxswapd v2i64:$src)), (XXPERMDI $src, $src, 2)>;
def : Pat<(v4f32 (PPCxxswapd v4f32:$src)), (XXPERMDI $src, $src, 2)>;
def : Pat<(v4i32 (PPCxxswapd v4i32:$src)), (XXPERMDI $src, $src, 2)>;
def : Pat<(v2f64 (PPCswapNoChain v2f64:$src)), (XXPERMDI $src, $src, 2)>;
// PPCvecshl XT, XA, XA, 2 can be selected to both XXSLDWI XT,XA,XA,2 and
// XXSWAPD XT,XA (i.e. XXPERMDI XT,XA,XA,2), the later one is more profitable.
def : Pat<(v4i32 (PPCvecshl v4i32:$src, v4i32:$src, 2)), (XXPERMDI $src, $src, 2)>;
// Selects.
def : Pat<(v2f64 (selectcc i1:$lhs, i1:$rhs, v2f64:$tval, v2f64:$fval, SETLT)),
(SELECT_VSRC (CRANDC $lhs, $rhs), $tval, $fval)>;
def : Pat<(v2f64 (selectcc i1:$lhs, i1:$rhs, v2f64:$tval, v2f64:$fval, SETULT)),
(SELECT_VSRC (CRANDC $rhs, $lhs), $tval, $fval)>;
def : Pat<(v2f64 (selectcc i1:$lhs, i1:$rhs, v2f64:$tval, v2f64:$fval, SETLE)),
(SELECT_VSRC (CRORC $lhs, $rhs), $tval, $fval)>;
def : Pat<(v2f64 (selectcc i1:$lhs, i1:$rhs, v2f64:$tval, v2f64:$fval, SETULE)),
(SELECT_VSRC (CRORC $rhs, $lhs), $tval, $fval)>;
def : Pat<(v2f64 (selectcc i1:$lhs, i1:$rhs, v2f64:$tval, v2f64:$fval, SETEQ)),
(SELECT_VSRC (CREQV $lhs, $rhs), $tval, $fval)>;
def : Pat<(v2f64 (selectcc i1:$lhs, i1:$rhs, v2f64:$tval, v2f64:$fval, SETGE)),
(SELECT_VSRC (CRORC $rhs, $lhs), $tval, $fval)>;
def : Pat<(v2f64 (selectcc i1:$lhs, i1:$rhs, v2f64:$tval, v2f64:$fval, SETUGE)),
(SELECT_VSRC (CRORC $lhs, $rhs), $tval, $fval)>;
def : Pat<(v2f64 (selectcc i1:$lhs, i1:$rhs, v2f64:$tval, v2f64:$fval, SETGT)),
(SELECT_VSRC (CRANDC $rhs, $lhs), $tval, $fval)>;
def : Pat<(v2f64 (selectcc i1:$lhs, i1:$rhs, v2f64:$tval, v2f64:$fval, SETUGT)),
(SELECT_VSRC (CRANDC $lhs, $rhs), $tval, $fval)>;
def : Pat<(v2f64 (selectcc i1:$lhs, i1:$rhs, v2f64:$tval, v2f64:$fval, SETNE)),
(SELECT_VSRC (CRXOR $lhs, $rhs), $tval, $fval)>;
def : Pat<(f64 (selectcc i1:$lhs, i1:$rhs, f64:$tval, f64:$fval, SETLT)),
(SELECT_VSFRC (CRANDC $lhs, $rhs), $tval, $fval)>;
def : Pat<(f64 (selectcc i1:$lhs, i1:$rhs, f64:$tval, f64:$fval, SETULT)),
(SELECT_VSFRC (CRANDC $rhs, $lhs), $tval, $fval)>;
def : Pat<(f64 (selectcc i1:$lhs, i1:$rhs, f64:$tval, f64:$fval, SETLE)),
(SELECT_VSFRC (CRORC $lhs, $rhs), $tval, $fval)>;
def : Pat<(f64 (selectcc i1:$lhs, i1:$rhs, f64:$tval, f64:$fval, SETULE)),
(SELECT_VSFRC (CRORC $rhs, $lhs), $tval, $fval)>;
def : Pat<(f64 (selectcc i1:$lhs, i1:$rhs, f64:$tval, f64:$fval, SETEQ)),
(SELECT_VSFRC (CREQV $lhs, $rhs), $tval, $fval)>;
def : Pat<(f64 (selectcc i1:$lhs, i1:$rhs, f64:$tval, f64:$fval, SETGE)),
(SELECT_VSFRC (CRORC $rhs, $lhs), $tval, $fval)>;
def : Pat<(f64 (selectcc i1:$lhs, i1:$rhs, f64:$tval, f64:$fval, SETUGE)),
(SELECT_VSFRC (CRORC $lhs, $rhs), $tval, $fval)>;
def : Pat<(f64 (selectcc i1:$lhs, i1:$rhs, f64:$tval, f64:$fval, SETGT)),
(SELECT_VSFRC (CRANDC $rhs, $lhs), $tval, $fval)>;
def : Pat<(f64 (selectcc i1:$lhs, i1:$rhs, f64:$tval, f64:$fval, SETUGT)),
(SELECT_VSFRC (CRANDC $lhs, $rhs), $tval, $fval)>;
def : Pat<(f64 (selectcc i1:$lhs, i1:$rhs, f64:$tval, f64:$fval, SETNE)),
(SELECT_VSFRC (CRXOR $lhs, $rhs), $tval, $fval)>;
// Divides.
def : Pat<(int_ppc_vsx_xvdivsp v4f32:$A, v4f32:$B),
(XVDIVSP $A, $B)>;
def : Pat<(int_ppc_vsx_xvdivdp v2f64:$A, v2f64:$B),
(XVDIVDP $A, $B)>;
// Reciprocal estimate
def : Pat<(int_ppc_vsx_xvresp v4f32:$A),
(XVRESP $A)>;
def : Pat<(int_ppc_vsx_xvredp v2f64:$A),
(XVREDP $A)>;
// Recip. square root estimate
def : Pat<(int_ppc_vsx_xvrsqrtesp v4f32:$A),
(XVRSQRTESP $A)>;
def : Pat<(int_ppc_vsx_xvrsqrtedp v2f64:$A),
(XVRSQRTEDP $A)>;
// Vector selection
def : Pat<(v16i8 (vselect v16i8:$vA, v16i8:$vB, v16i8:$vC)),
(COPY_TO_REGCLASS
(XXSEL (COPY_TO_REGCLASS $vC, VSRC),
(COPY_TO_REGCLASS $vB, VSRC),
(COPY_TO_REGCLASS $vA, VSRC)), VRRC)>;
def : Pat<(v8i16 (vselect v8i16:$vA, v8i16:$vB, v8i16:$vC)),
(COPY_TO_REGCLASS
(XXSEL (COPY_TO_REGCLASS $vC, VSRC),
(COPY_TO_REGCLASS $vB, VSRC),
(COPY_TO_REGCLASS $vA, VSRC)), VRRC)>;
def : Pat<(vselect v4i32:$vA, v4i32:$vB, v4i32:$vC),
(XXSEL $vC, $vB, $vA)>;
def : Pat<(vselect v2i64:$vA, v2i64:$vB, v2i64:$vC),
(XXSEL $vC, $vB, $vA)>;
def : Pat<(vselect v4i32:$vA, v4f32:$vB, v4f32:$vC),
(XXSEL $vC, $vB, $vA)>;
def : Pat<(vselect v2i64:$vA, v2f64:$vB, v2f64:$vC),
(XXSEL $vC, $vB, $vA)>;
def : Pat<(v4f32 (fmaxnum v4f32:$src1, v4f32:$src2)),
(v4f32 (XVMAXSP $src1, $src2))>;
def : Pat<(v4f32 (fminnum v4f32:$src1, v4f32:$src2)),
(v4f32 (XVMINSP $src1, $src2))>;
def : Pat<(v2f64 (fmaxnum v2f64:$src1, v2f64:$src2)),
(v2f64 (XVMAXDP $src1, $src2))>;
def : Pat<(v2f64 (fminnum v2f64:$src1, v2f64:$src2)),
(v2f64 (XVMINDP $src1, $src2))>;
let Predicates = [IsLittleEndian] in {
def : Pat<(f64 (PPCfcfid (PPCmtvsra (i64 (vector_extract v2i64:$S, 0))))),
(f64 (XSCVSXDDP (COPY_TO_REGCLASS (XXPERMDI $S, $S, 2), VSFRC)))>;
def : Pat<(f64 (PPCfcfid (PPCmtvsra (i64 (vector_extract v2i64:$S, 1))))),
(f64 (XSCVSXDDP (COPY_TO_REGCLASS (f64 (COPY_TO_REGCLASS $S, VSRC)), VSFRC)))>;
def : Pat<(f64 (PPCfcfidu (PPCmtvsra (i64 (vector_extract v2i64:$S, 0))))),
(f64 (XSCVUXDDP (COPY_TO_REGCLASS (XXPERMDI $S, $S, 2), VSFRC)))>;
def : Pat<(f64 (PPCfcfidu (PPCmtvsra (i64 (vector_extract v2i64:$S, 1))))),
(f64 (XSCVUXDDP (COPY_TO_REGCLASS (f64 (COPY_TO_REGCLASS $S, VSRC)), VSFRC)))>;
} // IsLittleEndian
let Predicates = [IsBigEndian] in {
def : Pat<(f64 (PPCfcfid (PPCmtvsra (i64 (vector_extract v2i64:$S, 0))))),
(f64 (XSCVSXDDP (COPY_TO_REGCLASS $S, VSFRC)))>;
def : Pat<(f64 (PPCfcfid (PPCmtvsra (i64 (vector_extract v2i64:$S, 1))))),
(f64 (XSCVSXDDP (COPY_TO_REGCLASS (XXPERMDI $S, $S, 2), VSFRC)))>;
def : Pat<(f64 (PPCfcfidu (PPCmtvsra (i64 (vector_extract v2i64:$S, 0))))),
(f64 (XSCVUXDDP (COPY_TO_REGCLASS $S, VSFRC)))>;
def : Pat<(f64 (PPCfcfidu (PPCmtvsra (i64 (vector_extract v2i64:$S, 1))))),
(f64 (XSCVUXDDP (COPY_TO_REGCLASS (XXPERMDI $S, $S, 2), VSFRC)))>;
} // IsBigEndian
} // AddedComplexity
} // HasVSX
def FpMinMax {
dag F32Min = (COPY_TO_REGCLASS (XSMINDP (COPY_TO_REGCLASS $A, VSFRC),
(COPY_TO_REGCLASS $B, VSFRC)),
VSSRC);
dag F32Max = (COPY_TO_REGCLASS (XSMAXDP (COPY_TO_REGCLASS $A, VSFRC),
(COPY_TO_REGCLASS $B, VSFRC)),
VSSRC);
}
let AddedComplexity = 400, Predicates = [HasVSX] in {
// f32 Min.
def : Pat<(f32 (fminnum_ieee f32:$A, f32:$B)),
(f32 FpMinMax.F32Min)>;
def : Pat<(f32 (fminnum_ieee (fcanonicalize f32:$A), f32:$B)),
(f32 FpMinMax.F32Min)>;
def : Pat<(f32 (fminnum_ieee f32:$A, (fcanonicalize f32:$B))),
(f32 FpMinMax.F32Min)>;
def : Pat<(f32 (fminnum_ieee (fcanonicalize f32:$A), (fcanonicalize f32:$B))),
(f32 FpMinMax.F32Min)>;
// F32 Max.
def : Pat<(f32 (fmaxnum_ieee f32:$A, f32:$B)),
(f32 FpMinMax.F32Max)>;
def : Pat<(f32 (fmaxnum_ieee (fcanonicalize f32:$A), f32:$B)),
(f32 FpMinMax.F32Max)>;
def : Pat<(f32 (fmaxnum_ieee f32:$A, (fcanonicalize f32:$B))),
(f32 FpMinMax.F32Max)>;
def : Pat<(f32 (fmaxnum_ieee (fcanonicalize f32:$A), (fcanonicalize f32:$B))),
(f32 FpMinMax.F32Max)>;
// f64 Min.
def : Pat<(f64 (fminnum_ieee f64:$A, f64:$B)),
(f64 (XSMINDP $A, $B))>;
def : Pat<(f64 (fminnum_ieee (fcanonicalize f64:$A), f64:$B)),
(f64 (XSMINDP $A, $B))>;
def : Pat<(f64 (fminnum_ieee f64:$A, (fcanonicalize f64:$B))),
(f64 (XSMINDP $A, $B))>;
def : Pat<(f64 (fminnum_ieee (fcanonicalize f64:$A), (fcanonicalize f64:$B))),
(f64 (XSMINDP $A, $B))>;
// f64 Max.
def : Pat<(f64 (fmaxnum_ieee f64:$A, f64:$B)),
(f64 (XSMAXDP $A, $B))>;
def : Pat<(f64 (fmaxnum_ieee (fcanonicalize f64:$A), f64:$B)),
(f64 (XSMAXDP $A, $B))>;
def : Pat<(f64 (fmaxnum_ieee f64:$A, (fcanonicalize f64:$B))),
(f64 (XSMAXDP $A, $B))>;
def : Pat<(f64 (fmaxnum_ieee (fcanonicalize f64:$A), (fcanonicalize f64:$B))),
(f64 (XSMAXDP $A, $B))>;
}
def ScalarLoads {
dag Li8 = (i32 (extloadi8 xoaddr:$src));
dag ZELi8 = (i32 (zextloadi8 xoaddr:$src));
dag ZELi8i64 = (i64 (zextloadi8 xoaddr:$src));
dag SELi8 = (i32 (sext_inreg (extloadi8 xoaddr:$src), i8));
dag SELi8i64 = (i64 (sext_inreg (extloadi8 xoaddr:$src), i8));
dag Li16 = (i32 (extloadi16 xoaddr:$src));
dag ZELi16 = (i32 (zextloadi16 xoaddr:$src));
dag ZELi16i64 = (i64 (zextloadi16 xoaddr:$src));
dag SELi16 = (i32 (sextloadi16 xoaddr:$src));
dag SELi16i64 = (i64 (sextloadi16 xoaddr:$src));
dag Li32 = (i32 (load xoaddr:$src));
}
def DWToSPExtractConv {
dag El0US1 = (f32 (PPCfcfidus
(f64 (PPCmtvsra (i64 (vector_extract v2i64:$S1, 0))))));
dag El1US1 = (f32 (PPCfcfidus
(f64 (PPCmtvsra (i64 (vector_extract v2i64:$S1, 1))))));
dag El0US2 = (f32 (PPCfcfidus
(f64 (PPCmtvsra (i64 (vector_extract v2i64:$S2, 0))))));
dag El1US2 = (f32 (PPCfcfidus
(f64 (PPCmtvsra (i64 (vector_extract v2i64:$S2, 1))))));
dag El0SS1 = (f32 (PPCfcfids
(f64 (PPCmtvsra (i64 (vector_extract v2i64:$S1, 0))))));
dag El1SS1 = (f32 (PPCfcfids
(f64 (PPCmtvsra (i64 (vector_extract v2i64:$S1, 1))))));
dag El0SS2 = (f32 (PPCfcfids
(f64 (PPCmtvsra (i64 (vector_extract v2i64:$S2, 0))))));
dag El1SS2 = (f32 (PPCfcfids
(f64 (PPCmtvsra (i64 (vector_extract v2i64:$S2, 1))))));
dag BVU = (v4f32 (build_vector El0US1, El1US1, El0US2, El1US2));
dag BVS = (v4f32 (build_vector El0SS1, El1SS1, El0SS2, El1SS2));
}
// The following VSX instructions were introduced in Power ISA 2.07
/* FIXME: if the operands are v2i64, these patterns will not match.
we should define new patterns or otherwise match the same patterns
when the elements are larger than i32.
*/
def HasP8Vector : Predicate<"PPCSubTarget->hasP8Vector()">;
def HasDirectMove : Predicate<"PPCSubTarget->hasDirectMove()">;
def NoP9Vector : Predicate<"!PPCSubTarget->hasP9Vector()">;
let Predicates = [HasP8Vector] in {
let AddedComplexity = 400 in { // Prefer VSX patterns over non-VSX patterns.
let isCommutable = 1 in {
def XXLEQV : XX3Form<60, 186,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xxleqv $XT, $XA, $XB", IIC_VecGeneral,
[(set v4i32:$XT, (vnot_ppc (xor v4i32:$XA, v4i32:$XB)))]>;
def XXLNAND : XX3Form<60, 178,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xxlnand $XT, $XA, $XB", IIC_VecGeneral,
[(set v4i32:$XT, (vnot_ppc (and v4i32:$XA,
v4i32:$XB)))]>;
} // isCommutable
def : Pat<(int_ppc_vsx_xxleqv v4i32:$A, v4i32:$B),
(XXLEQV $A, $B)>;
let isCodeGenOnly = 1, isMoveImm = 1, isAsCheapAsAMove = 1,
isReMaterializable = 1 in {
def XXLEQVOnes : XX3Form_SameOp<60, 186, (outs vsrc:$XT), (ins),
"xxleqv $XT, $XT, $XT", IIC_VecGeneral,
[(set v4i32:$XT, (bitconvert (v16i8 immAllOnesV)))]>;
}
def XXLORC : XX3Form<60, 170,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xxlorc $XT, $XA, $XB", IIC_VecGeneral,
[(set v4i32:$XT, (or v4i32:$XA, (vnot_ppc v4i32:$XB)))]>;
// VSX scalar loads introduced in ISA 2.07
let mayLoad = 1, mayStore = 0 in {
let CodeSize = 3 in
def LXSSPX : XX1Form_memOp<31, 524, (outs vssrc:$XT), (ins memrr:$src),
"lxsspx $XT, $src", IIC_LdStLFD, []>;
def LXSIWAX : XX1Form_memOp<31, 76, (outs vsfrc:$XT), (ins memrr:$src),
"lxsiwax $XT, $src", IIC_LdStLFD, []>;
def LXSIWZX : XX1Form_memOp<31, 12, (outs vsfrc:$XT), (ins memrr:$src),
"lxsiwzx $XT, $src", IIC_LdStLFD, []>;
// Pseudo instruction XFLOADf32 will be expanded to LXSSPX or LFSX later
let CodeSize = 3 in
def XFLOADf32 : PseudoXFormMemOp<(outs vssrc:$XT), (ins memrr:$src),
"#XFLOADf32",
[(set f32:$XT, (load xoaddr:$src))]>;
// Pseudo instruction LIWAX will be expanded to LXSIWAX or LFIWAX later
def LIWAX : PseudoXFormMemOp<(outs vsfrc:$XT), (ins memrr:$src),
"#LIWAX",
[(set f64:$XT, (PPClfiwax xoaddr:$src))]>;
// Pseudo instruction LIWZX will be expanded to LXSIWZX or LFIWZX later
def LIWZX : PseudoXFormMemOp<(outs vsfrc:$XT), (ins memrr:$src),
"#LIWZX",
[(set f64:$XT, (PPClfiwzx xoaddr:$src))]>;
} // mayLoad
// VSX scalar stores introduced in ISA 2.07
let mayStore = 1, mayLoad = 0 in {
let CodeSize = 3 in
def STXSSPX : XX1Form_memOp<31, 652, (outs), (ins vssrc:$XT, memrr:$dst),
"stxsspx $XT, $dst", IIC_LdStSTFD, []>;
def STXSIWX : XX1Form_memOp<31, 140, (outs), (ins vsfrc:$XT, memrr:$dst),
"stxsiwx $XT, $dst", IIC_LdStSTFD, []>;
// Pseudo instruction XFSTOREf32 will be expanded to STXSSPX or STFSX later
let CodeSize = 3 in
def XFSTOREf32 : PseudoXFormMemOp<(outs), (ins vssrc:$XT, memrr:$dst),
"#XFSTOREf32",
[(store f32:$XT, xoaddr:$dst)]>;
// Pseudo instruction STIWX will be expanded to STXSIWX or STFIWX later
def STIWX : PseudoXFormMemOp<(outs), (ins vsfrc:$XT, memrr:$dst),
"#STIWX",
[(PPCstfiwx f64:$XT, xoaddr:$dst)]>;
} // mayStore
def : Pat<(f64 (extloadf32 xoaddr:$src)),
(COPY_TO_REGCLASS (XFLOADf32 xoaddr:$src), VSFRC)>;
def : Pat<(f32 (fpround (f64 (extloadf32 xoaddr:$src)))),
(f32 (XFLOADf32 xoaddr:$src))>;
def : Pat<(f64 (fpextend f32:$src)),
(COPY_TO_REGCLASS $src, VSFRC)>;
def : Pat<(f32 (selectcc i1:$lhs, i1:$rhs, f32:$tval, f32:$fval, SETLT)),
(SELECT_VSSRC (CRANDC $lhs, $rhs), $tval, $fval)>;
def : Pat<(f32 (selectcc i1:$lhs, i1:$rhs, f32:$tval, f32:$fval, SETULT)),
(SELECT_VSSRC (CRANDC $rhs, $lhs), $tval, $fval)>;
def : Pat<(f32 (selectcc i1:$lhs, i1:$rhs, f32:$tval, f32:$fval, SETLE)),
(SELECT_VSSRC (CRORC $lhs, $rhs), $tval, $fval)>;
def : Pat<(f32 (selectcc i1:$lhs, i1:$rhs, f32:$tval, f32:$fval, SETULE)),
(SELECT_VSSRC (CRORC $rhs, $lhs), $tval, $fval)>;
def : Pat<(f32 (selectcc i1:$lhs, i1:$rhs, f32:$tval, f32:$fval, SETEQ)),
(SELECT_VSSRC (CREQV $lhs, $rhs), $tval, $fval)>;
def : Pat<(f32 (selectcc i1:$lhs, i1:$rhs, f32:$tval, f32:$fval, SETGE)),
(SELECT_VSSRC (CRORC $rhs, $lhs), $tval, $fval)>;
def : Pat<(f32 (selectcc i1:$lhs, i1:$rhs, f32:$tval, f32:$fval, SETUGE)),
(SELECT_VSSRC (CRORC $lhs, $rhs), $tval, $fval)>;
def : Pat<(f32 (selectcc i1:$lhs, i1:$rhs, f32:$tval, f32:$fval, SETGT)),
(SELECT_VSSRC (CRANDC $rhs, $lhs), $tval, $fval)>;
def : Pat<(f32 (selectcc i1:$lhs, i1:$rhs, f32:$tval, f32:$fval, SETUGT)),
(SELECT_VSSRC (CRANDC $lhs, $rhs), $tval, $fval)>;
def : Pat<(f32 (selectcc i1:$lhs, i1:$rhs, f32:$tval, f32:$fval, SETNE)),
(SELECT_VSSRC (CRXOR $lhs, $rhs), $tval, $fval)>;
// VSX Elementary Scalar FP arithmetic (SP)
let isCommutable = 1 in {
def XSADDSP : XX3Form<60, 0,
(outs vssrc:$XT), (ins vssrc:$XA, vssrc:$XB),
"xsaddsp $XT, $XA, $XB", IIC_VecFP,
[(set f32:$XT, (fadd f32:$XA, f32:$XB))]>;
def XSMULSP : XX3Form<60, 16,
(outs vssrc:$XT), (ins vssrc:$XA, vssrc:$XB),
"xsmulsp $XT, $XA, $XB", IIC_VecFP,
[(set f32:$XT, (fmul f32:$XA, f32:$XB))]>;
} // isCommutable
def XSSUBSP : XX3Form<60, 8,
(outs vssrc:$XT), (ins vssrc:$XA, vssrc:$XB),
"xssubsp $XT, $XA, $XB", IIC_VecFP,
[(set f32:$XT, (fsub f32:$XA, f32:$XB))]>;
def XSDIVSP : XX3Form<60, 24,
(outs vssrc:$XT), (ins vssrc:$XA, vssrc:$XB),
"xsdivsp $XT, $XA, $XB", IIC_FPDivS,
[(set f32:$XT, (fdiv f32:$XA, f32:$XB))]>;
def XSRESP : XX2Form<60, 26,
(outs vssrc:$XT), (ins vssrc:$XB),
"xsresp $XT, $XB", IIC_VecFP,
[(set f32:$XT, (PPCfre f32:$XB))]>;
def XSRSP : XX2Form<60, 281,
(outs vssrc:$XT), (ins vsfrc:$XB),
"xsrsp $XT, $XB", IIC_VecFP, []>;
def XSSQRTSP : XX2Form<60, 11,
(outs vssrc:$XT), (ins vssrc:$XB),
"xssqrtsp $XT, $XB", IIC_FPSqrtS,
[(set f32:$XT, (fsqrt f32:$XB))]>;
def XSRSQRTESP : XX2Form<60, 10,
(outs vssrc:$XT), (ins vssrc:$XB),
"xsrsqrtesp $XT, $XB", IIC_VecFP,
[(set f32:$XT, (PPCfrsqrte f32:$XB))]>;
// FMA Instructions
let BaseName = "XSMADDASP" in {
let isCommutable = 1 in
def XSMADDASP : XX3Form<60, 1,
(outs vssrc:$XT),
(ins vssrc:$XTi, vssrc:$XA, vssrc:$XB),
"xsmaddasp $XT, $XA, $XB", IIC_VecFP,
[(set f32:$XT, (fma f32:$XA, f32:$XB, f32:$XTi))]>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
let IsVSXFMAAlt = 1 in
def XSMADDMSP : XX3Form<60, 9,
(outs vssrc:$XT),
(ins vssrc:$XTi, vssrc:$XA, vssrc:$XB),
"xsmaddmsp $XT, $XA, $XB", IIC_VecFP, []>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
}
let BaseName = "XSMSUBASP" in {
let isCommutable = 1 in
def XSMSUBASP : XX3Form<60, 17,
(outs vssrc:$XT),
(ins vssrc:$XTi, vssrc:$XA, vssrc:$XB),
"xsmsubasp $XT, $XA, $XB", IIC_VecFP,
[(set f32:$XT, (fma f32:$XA, f32:$XB,
(fneg f32:$XTi)))]>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
let IsVSXFMAAlt = 1 in
def XSMSUBMSP : XX3Form<60, 25,
(outs vssrc:$XT),
(ins vssrc:$XTi, vssrc:$XA, vssrc:$XB),
"xsmsubmsp $XT, $XA, $XB", IIC_VecFP, []>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
}
let BaseName = "XSNMADDASP" in {
let isCommutable = 1 in
def XSNMADDASP : XX3Form<60, 129,
(outs vssrc:$XT),
(ins vssrc:$XTi, vssrc:$XA, vssrc:$XB),
"xsnmaddasp $XT, $XA, $XB", IIC_VecFP,
[(set f32:$XT, (fneg (fma f32:$XA, f32:$XB,
f32:$XTi)))]>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
let IsVSXFMAAlt = 1 in
def XSNMADDMSP : XX3Form<60, 137,
(outs vssrc:$XT),
(ins vssrc:$XTi, vssrc:$XA, vssrc:$XB),
"xsnmaddmsp $XT, $XA, $XB", IIC_VecFP, []>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
}
let BaseName = "XSNMSUBASP" in {
let isCommutable = 1 in
def XSNMSUBASP : XX3Form<60, 145,
(outs vssrc:$XT),
(ins vssrc:$XTi, vssrc:$XA, vssrc:$XB),
"xsnmsubasp $XT, $XA, $XB", IIC_VecFP,
[(set f32:$XT, (fneg (fma f32:$XA, f32:$XB,
(fneg f32:$XTi))))]>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
let IsVSXFMAAlt = 1 in
def XSNMSUBMSP : XX3Form<60, 153,
(outs vssrc:$XT),
(ins vssrc:$XTi, vssrc:$XA, vssrc:$XB),
"xsnmsubmsp $XT, $XA, $XB", IIC_VecFP, []>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
}
// Additional xsnmsubasp patterns: -a*b + c == -(a*b - c)
def : Pat<(fma (fneg f32:$A), f32:$B, f32:$C),
(XSNMSUBASP $C, $A, $B)>;
def : Pat<(fma f32:$A, (fneg f32:$B), f32:$C),
(XSNMSUBASP $C, $A, $B)>;
// Single Precision Conversions (FP <-> INT)
def XSCVSXDSP : XX2Form<60, 312,
(outs vssrc:$XT), (ins vsfrc:$XB),
"xscvsxdsp $XT, $XB", IIC_VecFP,
[(set f32:$XT, (PPCfcfids f64:$XB))]>;
def XSCVUXDSP : XX2Form<60, 296,
(outs vssrc:$XT), (ins vsfrc:$XB),
"xscvuxdsp $XT, $XB", IIC_VecFP,
[(set f32:$XT, (PPCfcfidus f64:$XB))]>;
// Conversions between vector and scalar single precision
def XSCVDPSPN : XX2Form<60, 267, (outs vsrc:$XT), (ins vssrc:$XB),
"xscvdpspn $XT, $XB", IIC_VecFP, []>;
def XSCVSPDPN : XX2Form<60, 331, (outs vssrc:$XT), (ins vsrc:$XB),
"xscvspdpn $XT, $XB", IIC_VecFP, []>;
let Predicates = [IsLittleEndian] in {
def : Pat<DWToSPExtractConv.El0SS1,
(f32 (XSCVSXDSP (COPY_TO_REGCLASS (XXPERMDI $S1, $S1, 2), VSFRC)))>;
def : Pat<DWToSPExtractConv.El1SS1,
(f32 (XSCVSXDSP (COPY_TO_REGCLASS
(f64 (COPY_TO_REGCLASS $S1, VSRC)), VSFRC)))>;
def : Pat<DWToSPExtractConv.El0US1,
(f32 (XSCVUXDSP (COPY_TO_REGCLASS (XXPERMDI $S1, $S1, 2), VSFRC)))>;
def : Pat<DWToSPExtractConv.El1US1,
(f32 (XSCVUXDSP (COPY_TO_REGCLASS
(f64 (COPY_TO_REGCLASS $S1, VSRC)), VSFRC)))>;
}
let Predicates = [IsBigEndian] in {
def : Pat<DWToSPExtractConv.El0SS1,
(f32 (XSCVSXDSP (COPY_TO_REGCLASS $S1, VSFRC)))>;
def : Pat<DWToSPExtractConv.El1SS1,
(f32 (XSCVSXDSP (COPY_TO_REGCLASS (XXPERMDI $S1, $S1, 2), VSFRC)))>;
def : Pat<DWToSPExtractConv.El0US1,
(f32 (XSCVUXDSP (COPY_TO_REGCLASS $S1, VSFRC)))>;
def : Pat<DWToSPExtractConv.El1US1,
(f32 (XSCVUXDSP (COPY_TO_REGCLASS (XXPERMDI $S1, $S1, 2), VSFRC)))>;
}
// Instructions for converting float to i64 feeding a store.
let Predicates = [NoP9Vector] in {
def : Pat<(PPCstore_scal_int_from_vsr
(f64 (PPCcv_fp_to_sint_in_vsr f64:$src)), xoaddr:$dst, 8),
(STXSDX (XSCVDPSXDS f64:$src), xoaddr:$dst)>;
def : Pat<(PPCstore_scal_int_from_vsr
(f64 (PPCcv_fp_to_uint_in_vsr f64:$src)), xoaddr:$dst, 8),
(STXSDX (XSCVDPUXDS f64:$src), xoaddr:$dst)>;
}
// Instructions for converting float to i32 feeding a store.
def : Pat<(PPCstore_scal_int_from_vsr
(f64 (PPCcv_fp_to_sint_in_vsr f64:$src)), xoaddr:$dst, 4),
(STIWX (XSCVDPSXWS f64:$src), xoaddr:$dst)>;
def : Pat<(PPCstore_scal_int_from_vsr
(f64 (PPCcv_fp_to_uint_in_vsr f64:$src)), xoaddr:$dst, 4),
(STIWX (XSCVDPUXWS f64:$src), xoaddr:$dst)>;
def : Pat<(v2i64 (smax v2i64:$src1, v2i64:$src2)),
(v2i64 (VMAXSD (COPY_TO_REGCLASS $src1, VRRC),
(COPY_TO_REGCLASS $src2, VRRC)))>;
def : Pat<(v2i64 (umax v2i64:$src1, v2i64:$src2)),
(v2i64 (VMAXUD (COPY_TO_REGCLASS $src1, VRRC),
(COPY_TO_REGCLASS $src2, VRRC)))>;
def : Pat<(v2i64 (smin v2i64:$src1, v2i64:$src2)),
(v2i64 (VMINSD (COPY_TO_REGCLASS $src1, VRRC),
(COPY_TO_REGCLASS $src2, VRRC)))>;
def : Pat<(v2i64 (umin v2i64:$src1, v2i64:$src2)),
(v2i64 (VMINUD (COPY_TO_REGCLASS $src1, VRRC),
(COPY_TO_REGCLASS $src2, VRRC)))>;
} // AddedComplexity = 400
} // HasP8Vector
let AddedComplexity = 400 in {
let Predicates = [HasDirectMove] in {
// VSX direct move instructions
def MFVSRD : XX1_RS6_RD5_XO<31, 51, (outs g8rc:$rA), (ins vsfrc:$XT),
"mfvsrd $rA, $XT", IIC_VecGeneral,
[(set i64:$rA, (PPCmfvsr f64:$XT))]>,
Requires<[In64BitMode]>;
let isCodeGenOnly = 1 in
def MFVRD : XX1_RS6_RD5_XO<31, 51, (outs g8rc:$rA), (ins vsrc:$XT),
"mfvsrd $rA, $XT", IIC_VecGeneral,
[]>,
Requires<[In64BitMode]>;
def MFVSRWZ : XX1_RS6_RD5_XO<31, 115, (outs gprc:$rA), (ins vsfrc:$XT),
"mfvsrwz $rA, $XT", IIC_VecGeneral,
[(set i32:$rA, (PPCmfvsr f64:$XT))]>;
let isCodeGenOnly = 1 in
def MFVRWZ : XX1_RS6_RD5_XO<31, 115, (outs gprc:$rA), (ins vsrc:$XT),
"mfvsrwz $rA, $XT", IIC_VecGeneral,
[]>;
def MTVSRD : XX1_RS6_RD5_XO<31, 179, (outs vsfrc:$XT), (ins g8rc:$rA),
"mtvsrd $XT, $rA", IIC_VecGeneral,
[(set f64:$XT, (PPCmtvsra i64:$rA))]>,
Requires<[In64BitMode]>;
let isCodeGenOnly = 1 in
def MTVRD : XX1_RS6_RD5_XO<31, 179, (outs vsrc:$XT), (ins g8rc:$rA),
"mtvsrd $XT, $rA", IIC_VecGeneral,
[]>,
Requires<[In64BitMode]>;
def MTVSRWA : XX1_RS6_RD5_XO<31, 211, (outs vsfrc:$XT), (ins gprc:$rA),
"mtvsrwa $XT, $rA", IIC_VecGeneral,
[(set f64:$XT, (PPCmtvsra i32:$rA))]>;
let isCodeGenOnly = 1 in
def MTVRWA : XX1_RS6_RD5_XO<31, 211, (outs vsrc:$XT), (ins gprc:$rA),
"mtvsrwa $XT, $rA", IIC_VecGeneral,
[]>;
def MTVSRWZ : XX1_RS6_RD5_XO<31, 243, (outs vsfrc:$XT), (ins gprc:$rA),
"mtvsrwz $XT, $rA", IIC_VecGeneral,
[(set f64:$XT, (PPCmtvsrz i32:$rA))]>;
let isCodeGenOnly = 1 in
def MTVRWZ : XX1_RS6_RD5_XO<31, 243, (outs vsrc:$XT), (ins gprc:$rA),
"mtvsrwz $XT, $rA", IIC_VecGeneral,
[]>;
} // HasDirectMove
let Predicates = [IsISA3_0, HasDirectMove] in {
def MTVSRWS: XX1_RS6_RD5_XO<31, 403, (outs vsrc:$XT), (ins gprc:$rA),
"mtvsrws $XT, $rA", IIC_VecGeneral, []>;
def MTVSRDD: XX1Form<31, 435, (outs vsrc:$XT), (ins g8rc_nox0:$rA, g8rc:$rB),
"mtvsrdd $XT, $rA, $rB", IIC_VecGeneral,
[]>, Requires<[In64BitMode]>;
def MFVSRLD: XX1_RS6_RD5_XO<31, 307, (outs g8rc:$rA), (ins vsrc:$XT),
"mfvsrld $rA, $XT", IIC_VecGeneral,
[]>, Requires<[In64BitMode]>;
} // IsISA3_0, HasDirectMove
} // AddedComplexity = 400
// We want to parse this from asm, but we don't want to emit this as it would
// be emitted with a VSX reg. So leave Emit = 0 here.
def : InstAlias<"mfvrd $rA, $XT",
(MFVRD g8rc:$rA, vrrc:$XT), 0>;
def : InstAlias<"mffprd $rA, $src",
(MFVSRD g8rc:$rA, f8rc:$src)>;
def : InstAlias<"mtvrd $XT, $rA",
(MTVRD vrrc:$XT, g8rc:$rA), 0>;
def : InstAlias<"mtfprd $dst, $rA",
(MTVSRD f8rc:$dst, g8rc:$rA)>;
def : InstAlias<"mfvrwz $rA, $XT",
(MFVRWZ gprc:$rA, vrrc:$XT), 0>;
def : InstAlias<"mffprwz $rA, $src",
(MFVSRWZ gprc:$rA, f8rc:$src)>;
def : InstAlias<"mtvrwa $XT, $rA",
(MTVRWA vrrc:$XT, gprc:$rA), 0>;
def : InstAlias<"mtfprwa $dst, $rA",
(MTVSRWA f8rc:$dst, gprc:$rA)>;
def : InstAlias<"mtvrwz $XT, $rA",
(MTVRWZ vrrc:$XT, gprc:$rA), 0>;
def : InstAlias<"mtfprwz $dst, $rA",
(MTVSRWZ f8rc:$dst, gprc:$rA)>;
/* Direct moves of various widths from GPR's into VSR's. Each move lines
the value up into element 0 (both BE and LE). Namely, entities smaller than
a doubleword are shifted left and moved for BE. For LE, they're moved, then
swapped to go into the least significant element of the VSR.
*/
def MovesToVSR {
dag BE_BYTE_0 =
(MTVSRD
(RLDICR
(INSERT_SUBREG (i64 (IMPLICIT_DEF)), $A, sub_32), 56, 7));
dag BE_HALF_0 =
(MTVSRD
(RLDICR
(INSERT_SUBREG (i64 (IMPLICIT_DEF)), $A, sub_32), 48, 15));
dag BE_WORD_0 =
(MTVSRD
(RLDICR
(INSERT_SUBREG (i64 (IMPLICIT_DEF)), $A, sub_32), 32, 31));
dag BE_DWORD_0 = (MTVSRD $A);
dag LE_MTVSRW = (MTVSRD (INSERT_SUBREG (i64 (IMPLICIT_DEF)), $A, sub_32));
dag LE_WORD_1 = (v2i64 (INSERT_SUBREG (v2i64 (IMPLICIT_DEF)),
LE_MTVSRW, sub_64));
dag LE_WORD_0 = (XXPERMDI LE_WORD_1, LE_WORD_1, 2);
dag LE_DWORD_1 = (v2i64 (INSERT_SUBREG (v2i64 (IMPLICIT_DEF)),
BE_DWORD_0, sub_64));
dag LE_DWORD_0 = (XXPERMDI LE_DWORD_1, LE_DWORD_1, 2);
}
/* Patterns for extracting elements out of vectors. Integer elements are
extracted using direct move operations. Patterns for extracting elements
whose indices are not available at compile time are also provided with
various _VARIABLE_ patterns.
The numbering for the DAG's is for LE, but when used on BE, the correct
LE element can just be used (i.e. LE_BYTE_2 == BE_BYTE_13).
*/
def VectorExtractions {
// Doubleword extraction
dag LE_DWORD_0 =
(MFVSRD
(EXTRACT_SUBREG
(XXPERMDI (COPY_TO_REGCLASS $S, VSRC),
(COPY_TO_REGCLASS $S, VSRC), 2), sub_64));
dag LE_DWORD_1 = (MFVSRD
(EXTRACT_SUBREG
(v2i64 (COPY_TO_REGCLASS $S, VSRC)), sub_64));
// Word extraction
dag LE_WORD_0 = (MFVSRWZ (EXTRACT_SUBREG (XXPERMDI $S, $S, 2), sub_64));
dag LE_WORD_1 = (MFVSRWZ (EXTRACT_SUBREG (XXSLDWI $S, $S, 1), sub_64));
dag LE_WORD_2 = (MFVSRWZ (EXTRACT_SUBREG
(v2i64 (COPY_TO_REGCLASS $S, VSRC)), sub_64));
dag LE_WORD_3 = (MFVSRWZ (EXTRACT_SUBREG (XXSLDWI $S, $S, 3), sub_64));
// Halfword extraction
dag LE_HALF_0 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_0, 0, 48), sub_32));
dag LE_HALF_1 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_0, 48, 48), sub_32));
dag LE_HALF_2 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_0, 32, 48), sub_32));
dag LE_HALF_3 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_0, 16, 48), sub_32));
dag LE_HALF_4 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_1, 0, 48), sub_32));
dag LE_HALF_5 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_1, 48, 48), sub_32));
dag LE_HALF_6 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_1, 32, 48), sub_32));
dag LE_HALF_7 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_1, 16, 48), sub_32));
// Byte extraction
dag LE_BYTE_0 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_0, 0, 56), sub_32));
dag LE_BYTE_1 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_0, 56, 56), sub_32));
dag LE_BYTE_2 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_0, 48, 56), sub_32));
dag LE_BYTE_3 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_0, 40, 56), sub_32));
dag LE_BYTE_4 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_0, 32, 56), sub_32));
dag LE_BYTE_5 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_0, 24, 56), sub_32));
dag LE_BYTE_6 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_0, 16, 56), sub_32));
dag LE_BYTE_7 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_0, 8, 56), sub_32));
dag LE_BYTE_8 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_1, 0, 56), sub_32));
dag LE_BYTE_9 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_1, 56, 56), sub_32));
dag LE_BYTE_10 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_1, 48, 56), sub_32));
dag LE_BYTE_11 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_1, 40, 56), sub_32));
dag LE_BYTE_12 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_1, 32, 56), sub_32));
dag LE_BYTE_13 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_1, 24, 56), sub_32));
dag LE_BYTE_14 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_1, 16, 56), sub_32));
dag LE_BYTE_15 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_1, 8, 56), sub_32));
/* Variable element number (BE and LE patterns must be specified separately)
This is a rather involved process.
Conceptually, this is how the move is accomplished:
1. Identify which doubleword contains the element
2. Shift in the VMX register so that the correct doubleword is correctly
lined up for the MFVSRD
3. Perform the move so that the element (along with some extra stuff)
is in the GPR
4. Right shift within the GPR so that the element is right-justified
Of course, the index is an element number which has a different meaning
on LE/BE so the patterns have to be specified separately.
Note: The final result will be the element right-justified with high
order bits being arbitrarily defined (namely, whatever was in the
vector register to the left of the value originally).
*/
/* LE variable byte
Number 1. above:
- For elements 0-7, we shift left by 8 bytes since they're on the right
- For elements 8-15, we need not shift (shift left by zero bytes)
This is accomplished by inverting the bits of the index and AND-ing
with 0x8 (i.e. clearing all bits of the index and inverting bit 60).
*/
dag LE_VBYTE_PERM_VEC = (v16i8 (LVSL ZERO8, (ANDC8 (LI8 8), $Idx)));
// Number 2. above:
// - Now that we set up the shift amount, we shift in the VMX register
dag LE_VBYTE_PERMUTE = (v16i8 (VPERM $S, $S, LE_VBYTE_PERM_VEC));
// Number 3. above:
// - The doubleword containing our element is moved to a GPR
dag LE_MV_VBYTE = (MFVSRD
(EXTRACT_SUBREG
(v2i64 (COPY_TO_REGCLASS LE_VBYTE_PERMUTE, VSRC)),
sub_64));
/* Number 4. above:
- Truncate the element number to the range 0-7 (8-15 are symmetrical
and out of range values are truncated accordingly)
- Multiply by 8 as we need to shift right by the number of bits, not bytes
- Shift right in the GPR by the calculated value
*/
dag LE_VBYTE_SHIFT = (EXTRACT_SUBREG (RLDICR (AND8 (LI8 7), $Idx), 3, 60),
sub_32);
dag LE_VARIABLE_BYTE = (EXTRACT_SUBREG (SRD LE_MV_VBYTE, LE_VBYTE_SHIFT),
sub_32);
/* LE variable halfword
Number 1. above:
- For elements 0-3, we shift left by 8 since they're on the right
- For elements 4-7, we need not shift (shift left by zero bytes)
Similarly to the byte pattern, we invert the bits of the index, but we
AND with 0x4 (i.e. clear all bits of the index and invert bit 61).
Of course, the shift is still by 8 bytes, so we must multiply by 2.
*/
dag LE_VHALF_PERM_VEC =
(v16i8 (LVSL ZERO8, (RLDICR (ANDC8 (LI8 4), $Idx), 1, 62)));
// Number 2. above:
// - Now that we set up the shift amount, we shift in the VMX register
dag LE_VHALF_PERMUTE = (v16i8 (VPERM $S, $S, LE_VHALF_PERM_VEC));
// Number 3. above:
// - The doubleword containing our element is moved to a GPR
dag LE_MV_VHALF = (MFVSRD
(EXTRACT_SUBREG
(v2i64 (COPY_TO_REGCLASS LE_VHALF_PERMUTE, VSRC)),
sub_64));
/* Number 4. above:
- Truncate the element number to the range 0-3 (4-7 are symmetrical
and out of range values are truncated accordingly)
- Multiply by 16 as we need to shift right by the number of bits
- Shift right in the GPR by the calculated value
*/
dag LE_VHALF_SHIFT = (EXTRACT_SUBREG (RLDICR (AND8 (LI8 3), $Idx), 4, 59),
sub_32);
dag LE_VARIABLE_HALF = (EXTRACT_SUBREG (SRD LE_MV_VHALF, LE_VHALF_SHIFT),
sub_32);
/* LE variable word
Number 1. above:
- For elements 0-1, we shift left by 8 since they're on the right
- For elements 2-3, we need not shift
*/
dag LE_VWORD_PERM_VEC = (v16i8 (LVSL ZERO8,
(RLDICR (ANDC8 (LI8 2), $Idx), 2, 61)));
// Number 2. above:
// - Now that we set up the shift amount, we shift in the VMX register
dag LE_VWORD_PERMUTE = (v16i8 (VPERM $S, $S, LE_VWORD_PERM_VEC));
// Number 3. above:
// - The doubleword containing our element is moved to a GPR
dag LE_MV_VWORD = (MFVSRD
(EXTRACT_SUBREG
(v2i64 (COPY_TO_REGCLASS LE_VWORD_PERMUTE, VSRC)),
sub_64));
/* Number 4. above:
- Truncate the element number to the range 0-1 (2-3 are symmetrical
and out of range values are truncated accordingly)
- Multiply by 32 as we need to shift right by the number of bits
- Shift right in the GPR by the calculated value
*/
dag LE_VWORD_SHIFT = (EXTRACT_SUBREG (RLDICR (AND8 (LI8 1), $Idx), 5, 58),
sub_32);
dag LE_VARIABLE_WORD = (EXTRACT_SUBREG (SRD LE_MV_VWORD, LE_VWORD_SHIFT),
sub_32);
/* LE variable doubleword
Number 1. above:
- For element 0, we shift left by 8 since it's on the right
- For element 1, we need not shift
*/
dag LE_VDWORD_PERM_VEC = (v16i8 (LVSL ZERO8,
(RLDICR (ANDC8 (LI8 1), $Idx), 3, 60)));
// Number 2. above:
// - Now that we set up the shift amount, we shift in the VMX register
dag LE_VDWORD_PERMUTE = (v16i8 (VPERM $S, $S, LE_VDWORD_PERM_VEC));
// Number 3. above:
// - The doubleword containing our element is moved to a GPR
// - Number 4. is not needed for the doubleword as the value is 64-bits
dag LE_VARIABLE_DWORD =
(MFVSRD (EXTRACT_SUBREG
(v2i64 (COPY_TO_REGCLASS LE_VDWORD_PERMUTE, VSRC)),
sub_64));
/* LE variable float
- Shift the vector to line up the desired element to BE Word 0
- Convert 32-bit float to a 64-bit single precision float
*/
dag LE_VFLOAT_PERM_VEC = (v16i8 (LVSL ZERO8,
(RLDICR (XOR8 (LI8 3), $Idx), 2, 61)));
dag LE_VFLOAT_PERMUTE = (VPERM $S, $S, LE_VFLOAT_PERM_VEC);
dag LE_VARIABLE_FLOAT = (XSCVSPDPN LE_VFLOAT_PERMUTE);
/* LE variable double
Same as the LE doubleword except there is no move.
*/
dag LE_VDOUBLE_PERMUTE = (v16i8 (VPERM (v16i8 (COPY_TO_REGCLASS $S, VRRC)),
(v16i8 (COPY_TO_REGCLASS $S, VRRC)),
LE_VDWORD_PERM_VEC));
dag LE_VARIABLE_DOUBLE = (COPY_TO_REGCLASS LE_VDOUBLE_PERMUTE, VSRC);
/* BE variable byte
The algorithm here is the same as the LE variable byte except:
- The shift in the VMX register is by 0/8 for opposite element numbers so
we simply AND the element number with 0x8
- The order of elements after the move to GPR is reversed, so we invert
the bits of the index prior to truncating to the range 0-7
*/
dag BE_VBYTE_PERM_VEC = (v16i8 (LVSL ZERO8, (ANDIo8 $Idx, 8)));
dag BE_VBYTE_PERMUTE = (v16i8 (VPERM $S, $S, BE_VBYTE_PERM_VEC));
dag BE_MV_VBYTE = (MFVSRD
(EXTRACT_SUBREG
(v2i64 (COPY_TO_REGCLASS BE_VBYTE_PERMUTE, VSRC)),
sub_64));
dag BE_VBYTE_SHIFT = (EXTRACT_SUBREG (RLDICR (ANDC8 (LI8 7), $Idx), 3, 60),
sub_32);
dag BE_VARIABLE_BYTE = (EXTRACT_SUBREG (SRD BE_MV_VBYTE, BE_VBYTE_SHIFT),
sub_32);
/* BE variable halfword
The algorithm here is the same as the LE variable halfword except:
- The shift in the VMX register is by 0/8 for opposite element numbers so
we simply AND the element number with 0x4 and multiply by 2
- The order of elements after the move to GPR is reversed, so we invert
the bits of the index prior to truncating to the range 0-3
*/
dag BE_VHALF_PERM_VEC = (v16i8 (LVSL ZERO8,
(RLDICR (ANDIo8 $Idx, 4), 1, 62)));
dag BE_VHALF_PERMUTE = (v16i8 (VPERM $S, $S, BE_VHALF_PERM_VEC));
dag BE_MV_VHALF = (MFVSRD
(EXTRACT_SUBREG
(v2i64 (COPY_TO_REGCLASS BE_VHALF_PERMUTE, VSRC)),
sub_64));
dag BE_VHALF_SHIFT = (EXTRACT_SUBREG (RLDICR (ANDC8 (LI8 3), $Idx), 4, 59),
sub_32);
dag BE_VARIABLE_HALF = (EXTRACT_SUBREG (SRD BE_MV_VHALF, BE_VHALF_SHIFT),
sub_32);
/* BE variable word
The algorithm is the same as the LE variable word except:
- The shift in the VMX register happens for opposite element numbers
- The order of elements after the move to GPR is reversed, so we invert
the bits of the index prior to truncating to the range 0-1
*/
dag BE_VWORD_PERM_VEC = (v16i8 (LVSL ZERO8,
(RLDICR (ANDIo8 $Idx, 2), 2, 61)));
dag BE_VWORD_PERMUTE = (v16i8 (VPERM $S, $S, BE_VWORD_PERM_VEC));
dag BE_MV_VWORD = (MFVSRD
(EXTRACT_SUBREG
(v2i64 (COPY_TO_REGCLASS BE_VWORD_PERMUTE, VSRC)),
sub_64));
dag BE_VWORD_SHIFT = (EXTRACT_SUBREG (RLDICR (ANDC8 (LI8 1), $Idx), 5, 58),
sub_32);
dag BE_VARIABLE_WORD = (EXTRACT_SUBREG (SRD BE_MV_VWORD, BE_VWORD_SHIFT),
sub_32);
/* BE variable doubleword
Same as the LE doubleword except we shift in the VMX register for opposite
element indices.
*/
dag BE_VDWORD_PERM_VEC = (v16i8 (LVSL ZERO8,
(RLDICR (ANDIo8 $Idx, 1), 3, 60)));
dag BE_VDWORD_PERMUTE = (v16i8 (VPERM $S, $S, BE_VDWORD_PERM_VEC));
dag BE_VARIABLE_DWORD =
(MFVSRD (EXTRACT_SUBREG
(v2i64 (COPY_TO_REGCLASS BE_VDWORD_PERMUTE, VSRC)),
sub_64));
/* BE variable float
- Shift the vector to line up the desired element to BE Word 0
- Convert 32-bit float to a 64-bit single precision float
*/
dag BE_VFLOAT_PERM_VEC = (v16i8 (LVSL ZERO8, (RLDICR $Idx, 2, 61)));
dag BE_VFLOAT_PERMUTE = (VPERM $S, $S, BE_VFLOAT_PERM_VEC);
dag BE_VARIABLE_FLOAT = (XSCVSPDPN BE_VFLOAT_PERMUTE);
/* BE variable double
Same as the BE doubleword except there is no move.
*/
dag BE_VDOUBLE_PERMUTE = (v16i8 (VPERM (v16i8 (COPY_TO_REGCLASS $S, VRRC)),
(v16i8 (COPY_TO_REGCLASS $S, VRRC)),
BE_VDWORD_PERM_VEC));
dag BE_VARIABLE_DOUBLE = (COPY_TO_REGCLASS BE_VDOUBLE_PERMUTE, VSRC);
}
def NoP9Altivec : Predicate<"!PPCSubTarget->hasP9Altivec()">;
let AddedComplexity = 400 in {
// v4f32 scalar <-> vector conversions (BE)
let Predicates = [IsBigEndian, HasP8Vector] in {
def : Pat<(v4f32 (scalar_to_vector f32:$A)),
(v4f32 (XSCVDPSPN $A))>;
def : Pat<(f32 (vector_extract v4f32:$S, 0)),
(f32 (XSCVSPDPN $S))>;
def : Pat<(f32 (vector_extract v4f32:$S, 1)),
(f32 (XSCVSPDPN (XXSLDWI $S, $S, 1)))>;
def : Pat<(f32 (vector_extract v4f32:$S, 2)),
(f32 (XSCVSPDPN (XXPERMDI $S, $S, 2)))>;
def : Pat<(f32 (vector_extract v4f32:$S, 3)),
(f32 (XSCVSPDPN (XXSLDWI $S, $S, 3)))>;
def : Pat<(f32 (vector_extract v4f32:$S, i64:$Idx)),
(f32 VectorExtractions.BE_VARIABLE_FLOAT)>;
} // IsBigEndian, HasP8Vector
// Variable index vector_extract for v2f64 does not require P8Vector
let Predicates = [IsBigEndian, HasVSX] in
def : Pat<(f64 (vector_extract v2f64:$S, i64:$Idx)),
(f64 VectorExtractions.BE_VARIABLE_DOUBLE)>;
let Predicates = [IsBigEndian, HasDirectMove] in {
// v16i8 scalar <-> vector conversions (BE)
def : Pat<(v16i8 (scalar_to_vector i32:$A)),
(v16i8 (SUBREG_TO_REG (i64 1), MovesToVSR.BE_BYTE_0, sub_64))>;
def : Pat<(v8i16 (scalar_to_vector i32:$A)),
(v8i16 (SUBREG_TO_REG (i64 1), MovesToVSR.BE_HALF_0, sub_64))>;
def : Pat<(v4i32 (scalar_to_vector i32:$A)),
(v4i32 (SUBREG_TO_REG (i64 1), MovesToVSR.BE_WORD_0, sub_64))>;
def : Pat<(v2i64 (scalar_to_vector i64:$A)),
(v2i64 (SUBREG_TO_REG (i64 1), MovesToVSR.BE_DWORD_0, sub_64))>;
// v2i64 scalar <-> vector conversions (BE)
def : Pat<(i64 (vector_extract v2i64:$S, 0)),
(i64 VectorExtractions.LE_DWORD_1)>;
def : Pat<(i64 (vector_extract v2i64:$S, 1)),
(i64 VectorExtractions.LE_DWORD_0)>;
def : Pat<(i64 (vector_extract v2i64:$S, i64:$Idx)),
(i64 VectorExtractions.BE_VARIABLE_DWORD)>;
} // IsBigEndian, HasDirectMove
let Predicates = [IsBigEndian, HasDirectMove, NoP9Altivec] in {
def : Pat<(i32 (vector_extract v16i8:$S, 0)),
(i32 VectorExtractions.LE_BYTE_15)>;
def : Pat<(i32 (vector_extract v16i8:$S, 1)),
(i32 VectorExtractions.LE_BYTE_14)>;
def : Pat<(i32 (vector_extract v16i8:$S, 2)),
(i32 VectorExtractions.LE_BYTE_13)>;
def : Pat<(i32 (vector_extract v16i8:$S, 3)),
(i32 VectorExtractions.LE_BYTE_12)>;
def : Pat<(i32 (vector_extract v16i8:$S, 4)),
(i32 VectorExtractions.LE_BYTE_11)>;
def : Pat<(i32 (vector_extract v16i8:$S, 5)),
(i32 VectorExtractions.LE_BYTE_10)>;
def : Pat<(i32 (vector_extract v16i8:$S, 6)),
(i32 VectorExtractions.LE_BYTE_9)>;
def : Pat<(i32 (vector_extract v16i8:$S, 7)),
(i32 VectorExtractions.LE_BYTE_8)>;
def : Pat<(i32 (vector_extract v16i8:$S, 8)),
(i32 VectorExtractions.LE_BYTE_7)>;
def : Pat<(i32 (vector_extract v16i8:$S, 9)),
(i32 VectorExtractions.LE_BYTE_6)>;
def : Pat<(i32 (vector_extract v16i8:$S, 10)),
(i32 VectorExtractions.LE_BYTE_5)>;
def : Pat<(i32 (vector_extract v16i8:$S, 11)),
(i32 VectorExtractions.LE_BYTE_4)>;
def : Pat<(i32 (vector_extract v16i8:$S, 12)),
(i32 VectorExtractions.LE_BYTE_3)>;
def : Pat<(i32 (vector_extract v16i8:$S, 13)),
(i32 VectorExtractions.LE_BYTE_2)>;
def : Pat<(i32 (vector_extract v16i8:$S, 14)),
(i32 VectorExtractions.LE_BYTE_1)>;
def : Pat<(i32 (vector_extract v16i8:$S, 15)),
(i32 VectorExtractions.LE_BYTE_0)>;
def : Pat<(i32 (vector_extract v16i8:$S, i64:$Idx)),
(i32 VectorExtractions.BE_VARIABLE_BYTE)>;
// v8i16 scalar <-> vector conversions (BE)
def : Pat<(i32 (vector_extract v8i16:$S, 0)),
(i32 VectorExtractions.LE_HALF_7)>;
def : Pat<(i32 (vector_extract v8i16:$S, 1)),
(i32 VectorExtractions.LE_HALF_6)>;
def : Pat<(i32 (vector_extract v8i16:$S, 2)),
(i32 VectorExtractions.LE_HALF_5)>;
def : Pat<(i32 (vector_extract v8i16:$S, 3)),
(i32 VectorExtractions.LE_HALF_4)>;
def : Pat<(i32 (vector_extract v8i16:$S, 4)),
(i32 VectorExtractions.LE_HALF_3)>;
def : Pat<(i32 (vector_extract v8i16:$S, 5)),
(i32 VectorExtractions.LE_HALF_2)>;
def : Pat<(i32 (vector_extract v8i16:$S, 6)),
(i32 VectorExtractions.LE_HALF_1)>;
def : Pat<(i32 (vector_extract v8i16:$S, 7)),
(i32 VectorExtractions.LE_HALF_0)>;
def : Pat<(i32 (vector_extract v8i16:$S, i64:$Idx)),
(i32 VectorExtractions.BE_VARIABLE_HALF)>;
// v4i32 scalar <-> vector conversions (BE)
def : Pat<(i32 (vector_extract v4i32:$S, 0)),
(i32 VectorExtractions.LE_WORD_3)>;
def : Pat<(i32 (vector_extract v4i32:$S, 1)),
(i32 VectorExtractions.LE_WORD_2)>;
def : Pat<(i32 (vector_extract v4i32:$S, 2)),
(i32 VectorExtractions.LE_WORD_1)>;
def : Pat<(i32 (vector_extract v4i32:$S, 3)),
(i32 VectorExtractions.LE_WORD_0)>;
def : Pat<(i32 (vector_extract v4i32:$S, i64:$Idx)),
(i32 VectorExtractions.BE_VARIABLE_WORD)>;
} // IsBigEndian, HasDirectMove, NoP9Altivec
// v4f32 scalar <-> vector conversions (LE)
let Predicates = [IsLittleEndian, HasP8Vector] in {
def : Pat<(v4f32 (scalar_to_vector f32:$A)),
(v4f32 (XXSLDWI (XSCVDPSPN $A), (XSCVDPSPN $A), 1))>;
def : Pat<(f32 (vector_extract v4f32:$S, 0)),
(f32 (XSCVSPDPN (XXSLDWI $S, $S, 3)))>;
def : Pat<(f32 (vector_extract v4f32:$S, 1)),
(f32 (XSCVSPDPN (XXPERMDI $S, $S, 2)))>;
def : Pat<(f32 (vector_extract v4f32:$S, 2)),
(f32 (XSCVSPDPN (XXSLDWI $S, $S, 1)))>;
def : Pat<(f32 (vector_extract v4f32:$S, 3)),
(f32 (XSCVSPDPN $S))>;
def : Pat<(f32 (vector_extract v4f32:$S, i64:$Idx)),
(f32 VectorExtractions.LE_VARIABLE_FLOAT)>;
} // IsLittleEndian, HasP8Vector
// Variable index vector_extract for v2f64 does not require P8Vector
let Predicates = [IsLittleEndian, HasVSX] in
def : Pat<(f64 (vector_extract v2f64:$S, i64:$Idx)),
(f64 VectorExtractions.LE_VARIABLE_DOUBLE)>;
def : Pat<(int_ppc_vsx_stxvd2x_be v2f64:$rS, xoaddr:$dst),
(STXVD2X $rS, xoaddr:$dst)>;
def : Pat<(int_ppc_vsx_stxvw4x_be v4i32:$rS, xoaddr:$dst),
(STXVW4X $rS, xoaddr:$dst)>;
def : Pat<(v4i32 (int_ppc_vsx_lxvw4x_be xoaddr:$src)), (LXVW4X xoaddr:$src)>;
def : Pat<(v2f64 (int_ppc_vsx_lxvd2x_be xoaddr:$src)), (LXVD2X xoaddr:$src)>;
// Variable index unsigned vector_extract on Power9
let Predicates = [HasP9Altivec, IsLittleEndian] in {
def : Pat<(i64 (anyext (i32 (vector_extract v16i8:$S, i64:$Idx)))),
(VEXTUBRX $Idx, $S)>;
def : Pat<(i64 (anyext (i32 (vector_extract v8i16:$S, i64:$Idx)))),
(VEXTUHRX (RLWINM8 $Idx, 1, 28, 30), $S)>;
def : Pat<(i64 (anyext (i32 (vector_extract v8i16:$S, 0)))),
(VEXTUHRX (LI8 0), $S)>;
def : Pat<(i64 (anyext (i32 (vector_extract v8i16:$S, 1)))),
(VEXTUHRX (LI8 2), $S)>;
def : Pat<(i64 (anyext (i32 (vector_extract v8i16:$S, 2)))),
(VEXTUHRX (LI8 4), $S)>;
def : Pat<(i64 (anyext (i32 (vector_extract v8i16:$S, 3)))),
(VEXTUHRX (LI8 6), $S)>;
def : Pat<(i64 (anyext (i32 (vector_extract v8i16:$S, 4)))),
(VEXTUHRX (LI8 8), $S)>;
def : Pat<(i64 (anyext (i32 (vector_extract v8i16:$S, 5)))),
(VEXTUHRX (LI8 10), $S)>;
def : Pat<(i64 (anyext (i32 (vector_extract v8i16:$S, 6)))),
(VEXTUHRX (LI8 12), $S)>;
def : Pat<(i64 (anyext (i32 (vector_extract v8i16:$S, 7)))),
(VEXTUHRX (LI8 14), $S)>;
def : Pat<(i64 (zext (i32 (vector_extract v4i32:$S, i64:$Idx)))),
(VEXTUWRX (RLWINM8 $Idx, 2, 28, 29), $S)>;
def : Pat<(i64 (zext (i32 (vector_extract v4i32:$S, 0)))),
(VEXTUWRX (LI8 0), $S)>;
def : Pat<(i64 (zext (i32 (vector_extract v4i32:$S, 1)))),
(VEXTUWRX (LI8 4), $S)>;
// For extracting LE word 2, MFVSRWZ is better than VEXTUWRX
def : Pat<(i64 (zext (i32 (vector_extract v4i32:$S, 2)))),
(INSERT_SUBREG (i64 (IMPLICIT_DEF)),
(i32 VectorExtractions.LE_WORD_2), sub_32)>;
def : Pat<(i64 (zext (i32 (vector_extract v4i32:$S, 3)))),
(VEXTUWRX (LI8 12), $S)>;
def : Pat<(i64 (sext (i32 (vector_extract v4i32:$S, i64:$Idx)))),
(EXTSW (VEXTUWRX (RLWINM8 $Idx, 2, 28, 29), $S))>;
def : Pat<(i64 (sext (i32 (vector_extract v4i32:$S, 0)))),
(EXTSW (VEXTUWRX (LI8 0), $S))>;
def : Pat<(i64 (sext (i32 (vector_extract v4i32:$S, 1)))),
(EXTSW (VEXTUWRX (LI8 4), $S))>;
// For extracting LE word 2, MFVSRWZ is better than VEXTUWRX
def : Pat<(i64 (sext (i32 (vector_extract v4i32:$S, 2)))),
(EXTSW (INSERT_SUBREG (i64 (IMPLICIT_DEF)),
(i32 VectorExtractions.LE_WORD_2), sub_32))>;
def : Pat<(i64 (sext (i32 (vector_extract v4i32:$S, 3)))),
(EXTSW (VEXTUWRX (LI8 12), $S))>;
def : Pat<(i32 (vector_extract v16i8:$S, i64:$Idx)),
(i32 (EXTRACT_SUBREG (VEXTUBRX $Idx, $S), sub_32))>;
def : Pat<(i32 (vector_extract v16i8:$S, 0)),
(i32 (EXTRACT_SUBREG (VEXTUBRX (LI8 0), $S), sub_32))>;
def : Pat<(i32 (vector_extract v16i8:$S, 1)),
(i32 (EXTRACT_SUBREG (VEXTUBRX (LI8 1), $S), sub_32))>;
def : Pat<(i32 (vector_extract v16i8:$S, 2)),
(i32 (EXTRACT_SUBREG (VEXTUBRX (LI8 2), $S), sub_32))>;
def : Pat<(i32 (vector_extract v16i8:$S, 3)),
(i32 (EXTRACT_SUBREG (VEXTUBRX (LI8 3), $S), sub_32))>;
def : Pat<(i32 (vector_extract v16i8:$S, 4)),
(i32 (EXTRACT_SUBREG (VEXTUBRX (LI8 4), $S), sub_32))>;
def : Pat<(i32 (vector_extract v16i8:$S, 5)),
(i32 (EXTRACT_SUBREG (VEXTUBRX (LI8 5), $S), sub_32))>;
def : Pat<(i32 (vector_extract v16i8:$S, 6)),
(i32 (EXTRACT_SUBREG (VEXTUBRX (LI8 6), $S), sub_32))>;
def : Pat<(i32 (vector_extract v16i8:$S, 7)),
(i32 (EXTRACT_SUBREG (VEXTUBRX (LI8 7), $S), sub_32))>;
def : Pat<(i32 (vector_extract v16i8:$S, 8)),
(i32 (EXTRACT_SUBREG (VEXTUBRX (LI8 8), $S), sub_32))>;
def : Pat<(i32 (vector_extract v16i8:$S, 9)),
(i32 (EXTRACT_SUBREG (VEXTUBRX (LI8 9), $S), sub_32))>;
def : Pat<(i32 (vector_extract v16i8:$S, 10)),
(i32 (EXTRACT_SUBREG (VEXTUBRX (LI8 10), $S), sub_32))>;
def : Pat<(i32 (vector_extract v16i8:$S, 11)),
(i32 (EXTRACT_SUBREG (VEXTUBRX (LI8 11), $S), sub_32))>;
def : Pat<(i32 (vector_extract v16i8:$S, 12)),
(i32 (EXTRACT_SUBREG (VEXTUBRX (LI8 12), $S), sub_32))>;
def : Pat<(i32 (vector_extract v16i8:$S, 13)),
(i32 (EXTRACT_SUBREG (VEXTUBRX (LI8 13), $S), sub_32))>;
def : Pat<(i32 (vector_extract v16i8:$S, 14)),
(i32 (EXTRACT_SUBREG (VEXTUBRX (LI8 14), $S), sub_32))>;
def : Pat<(i32 (vector_extract v16i8:$S, 15)),
(i32 (EXTRACT_SUBREG (VEXTUBRX (LI8 15), $S), sub_32))>;
def : Pat<(i32 (vector_extract v8i16:$S, i64:$Idx)),
(i32 (EXTRACT_SUBREG (VEXTUHRX
(RLWINM8 $Idx, 1, 28, 30), $S), sub_32))>;
def : Pat<(i32 (vector_extract v8i16:$S, 0)),
(i32 (EXTRACT_SUBREG (VEXTUHRX (LI8 0), $S), sub_32))>;
def : Pat<(i32 (vector_extract v8i16:$S, 1)),
(i32 (EXTRACT_SUBREG (VEXTUHRX (LI8 2), $S), sub_32))>;
def : Pat<(i32 (vector_extract v8i16:$S, 2)),
(i32 (EXTRACT_SUBREG (VEXTUHRX (LI8 4), $S), sub_32))>;
def : Pat<(i32 (vector_extract v8i16:$S, 3)),
(i32 (EXTRACT_SUBREG (VEXTUHRX (LI8 6), $S), sub_32))>;
def : Pat<(i32 (vector_extract v8i16:$S, 4)),
(i32 (EXTRACT_SUBREG (VEXTUHRX (LI8 8), $S), sub_32))>;
def : Pat<(i32 (vector_extract v8i16:$S, 5)),
(i32 (EXTRACT_SUBREG (VEXTUHRX (LI8 10), $S), sub_32))>;
def : Pat<(i32 (vector_extract v8i16:$S, 6)),
(i32 (EXTRACT_SUBREG (VEXTUHRX (LI8 12), $S), sub_32))>;
def : Pat<(i32 (vector_extract v8i16:$S, 6)),
(i32 (EXTRACT_SUBREG (VEXTUHRX (LI8 14), $S), sub_32))>;
def : Pat<(i32 (vector_extract v4i32:$S, i64:$Idx)),
(i32 (EXTRACT_SUBREG (VEXTUWRX
(RLWINM8 $Idx, 2, 28, 29), $S), sub_32))>;
def : Pat<(i32 (vector_extract v4i32:$S, 0)),
(i32 (EXTRACT_SUBREG (VEXTUWRX (LI8 0), $S), sub_32))>;
def : Pat<(i32 (vector_extract v4i32:$S, 1)),
(i32 (EXTRACT_SUBREG (VEXTUWRX (LI8 4), $S), sub_32))>;
// For extracting LE word 2, MFVSRWZ is better than VEXTUWRX
def : Pat<(i32 (vector_extract v4i32:$S, 2)),
(i32 VectorExtractions.LE_WORD_2)>;
def : Pat<(i32 (vector_extract v4i32:$S, 3)),
(i32 (EXTRACT_SUBREG (VEXTUWRX (LI8 12), $S), sub_32))>;
}
let Predicates = [HasP9Altivec, IsBigEndian] in {
def : Pat<(i64 (anyext (i32 (vector_extract v16i8:$S, i64:$Idx)))),
(VEXTUBLX $Idx, $S)>;
def : Pat<(i64 (anyext (i32 (vector_extract v8i16:$S, i64:$Idx)))),
(VEXTUHLX (RLWINM8 $Idx, 1, 28, 30), $S)>;
def : Pat<(i64 (anyext (i32 (vector_extract v8i16:$S, 0)))),
(VEXTUHLX (LI8 0), $S)>;
def : Pat<(i64 (anyext (i32 (vector_extract v8i16:$S, 1)))),
(VEXTUHLX (LI8 2), $S)>;
def : Pat<(i64 (anyext (i32 (vector_extract v8i16:$S, 2)))),
(VEXTUHLX (LI8 4), $S)>;
def : Pat<(i64 (anyext (i32 (vector_extract v8i16:$S, 3)))),
(VEXTUHLX (LI8 6), $S)>;
def : Pat<(i64 (anyext (i32 (vector_extract v8i16:$S, 4)))),
(VEXTUHLX (LI8 8), $S)>;
def : Pat<(i64 (anyext (i32 (vector_extract v8i16:$S, 5)))),
(VEXTUHLX (LI8 10), $S)>;
def : Pat<(i64 (anyext (i32 (vector_extract v8i16:$S, 6)))),
(VEXTUHLX (LI8 12), $S)>;
def : Pat<(i64 (anyext (i32 (vector_extract v8i16:$S, 7)))),
(VEXTUHLX (LI8 14), $S)>;
def : Pat<(i64 (zext (i32 (vector_extract v4i32:$S, i64:$Idx)))),
(VEXTUWLX (RLWINM8 $Idx, 2, 28, 29), $S)>;
def : Pat<(i64 (zext (i32 (vector_extract v4i32:$S, 0)))),
(VEXTUWLX (LI8 0), $S)>;
// For extracting BE word 1, MFVSRWZ is better than VEXTUWLX
def : Pat<(i64 (zext (i32 (vector_extract v4i32:$S, 1)))),
(INSERT_SUBREG (i64 (IMPLICIT_DEF)),
(i32 VectorExtractions.LE_WORD_2), sub_32)>;
def : Pat<(i64 (zext (i32 (vector_extract v4i32:$S, 2)))),
(VEXTUWLX (LI8 8), $S)>;
def : Pat<(i64 (zext (i32 (vector_extract v4i32:$S, 3)))),
(VEXTUWLX (LI8 12), $S)>;
def : Pat<(i64 (sext (i32 (vector_extract v4i32:$S, i64:$Idx)))),
(EXTSW (VEXTUWLX (RLWINM8 $Idx, 2, 28, 29), $S))>;
def : Pat<(i64 (sext (i32 (vector_extract v4i32:$S, 0)))),
(EXTSW (VEXTUWLX (LI8 0), $S))>;
// For extracting BE word 1, MFVSRWZ is better than VEXTUWLX
def : Pat<(i64 (sext (i32 (vector_extract v4i32:$S, 1)))),
(EXTSW (INSERT_SUBREG (i64 (IMPLICIT_DEF)),
(i32 VectorExtractions.LE_WORD_2), sub_32))>;
def : Pat<(i64 (sext (i32 (vector_extract v4i32:$S, 2)))),
(EXTSW (VEXTUWLX (LI8 8), $S))>;
def : Pat<(i64 (sext (i32 (vector_extract v4i32:$S, 3)))),
(EXTSW (VEXTUWLX (LI8 12), $S))>;
def : Pat<(i32 (vector_extract v16i8:$S, i64:$Idx)),
(i32 (EXTRACT_SUBREG (VEXTUBLX $Idx, $S), sub_32))>;
def : Pat<(i32 (vector_extract v16i8:$S, 0)),
(i32 (EXTRACT_SUBREG (VEXTUBLX (LI8 0), $S), sub_32))>;
def : Pat<(i32 (vector_extract v16i8:$S, 1)),
(i32 (EXTRACT_SUBREG (VEXTUBLX (LI8 1), $S), sub_32))>;
def : Pat<(i32 (vector_extract v16i8:$S, 2)),
(i32 (EXTRACT_SUBREG (VEXTUBLX (LI8 2), $S), sub_32))>;
def : Pat<(i32 (vector_extract v16i8:$S, 3)),
(i32 (EXTRACT_SUBREG (VEXTUBLX (LI8 3), $S), sub_32))>;
def : Pat<(i32 (vector_extract v16i8:$S, 4)),
(i32 (EXTRACT_SUBREG (VEXTUBLX (LI8 4), $S), sub_32))>;
def : Pat<(i32 (vector_extract v16i8:$S, 5)),
(i32 (EXTRACT_SUBREG (VEXTUBLX (LI8 5), $S), sub_32))>;
def : Pat<(i32 (vector_extract v16i8:$S, 6)),
(i32 (EXTRACT_SUBREG (VEXTUBLX (LI8 6), $S), sub_32))>;
def : Pat<(i32 (vector_extract v16i8:$S, 7)),
(i32 (EXTRACT_SUBREG (VEXTUBLX (LI8 7), $S), sub_32))>;
def : Pat<(i32 (vector_extract v16i8:$S, 8)),
(i32 (EXTRACT_SUBREG (VEXTUBLX (LI8 8), $S), sub_32))>;
def : Pat<(i32 (vector_extract v16i8:$S, 9)),
(i32 (EXTRACT_SUBREG (VEXTUBLX (LI8 9), $S), sub_32))>;
def : Pat<(i32 (vector_extract v16i8:$S, 10)),
(i32 (EXTRACT_SUBREG (VEXTUBLX (LI8 10), $S), sub_32))>;
def : Pat<(i32 (vector_extract v16i8:$S, 11)),
(i32 (EXTRACT_SUBREG (VEXTUBLX (LI8 11), $S), sub_32))>;
def : Pat<(i32 (vector_extract v16i8:$S, 12)),
(i32 (EXTRACT_SUBREG (VEXTUBLX (LI8 12), $S), sub_32))>;
def : Pat<(i32 (vector_extract v16i8:$S, 13)),
(i32 (EXTRACT_SUBREG (VEXTUBLX (LI8 13), $S), sub_32))>;
def : Pat<(i32 (vector_extract v16i8:$S, 14)),
(i32 (EXTRACT_SUBREG (VEXTUBLX (LI8 14), $S), sub_32))>;
def : Pat<(i32 (vector_extract v16i8:$S, 15)),
(i32 (EXTRACT_SUBREG (VEXTUBLX (LI8 15), $S), sub_32))>;
def : Pat<(i32 (vector_extract v8i16:$S, i64:$Idx)),
(i32 (EXTRACT_SUBREG (VEXTUHLX
(RLWINM8 $Idx, 1, 28, 30), $S), sub_32))>;
def : Pat<(i32 (vector_extract v8i16:$S, 0)),
(i32 (EXTRACT_SUBREG (VEXTUHLX (LI8 0), $S), sub_32))>;
def : Pat<(i32 (vector_extract v8i16:$S, 1)),
(i32 (EXTRACT_SUBREG (VEXTUHLX (LI8 2), $S), sub_32))>;
def : Pat<(i32 (vector_extract v8i16:$S, 2)),
(i32 (EXTRACT_SUBREG (VEXTUHLX (LI8 4), $S), sub_32))>;
def : Pat<(i32 (vector_extract v8i16:$S, 3)),
(i32 (EXTRACT_SUBREG (VEXTUHLX (LI8 6), $S), sub_32))>;
def : Pat<(i32 (vector_extract v8i16:$S, 4)),
(i32 (EXTRACT_SUBREG (VEXTUHLX (LI8 8), $S), sub_32))>;
def : Pat<(i32 (vector_extract v8i16:$S, 5)),
(i32 (EXTRACT_SUBREG (VEXTUHLX (LI8 10), $S), sub_32))>;
def : Pat<(i32 (vector_extract v8i16:$S, 6)),
(i32 (EXTRACT_SUBREG (VEXTUHLX (LI8 12), $S), sub_32))>;
def : Pat<(i32 (vector_extract v8i16:$S, 6)),
(i32 (EXTRACT_SUBREG (VEXTUHLX (LI8 14), $S), sub_32))>;
def : Pat<(i32 (vector_extract v4i32:$S, i64:$Idx)),
(i32 (EXTRACT_SUBREG (VEXTUWLX
(RLWINM8 $Idx, 2, 28, 29), $S), sub_32))>;
def : Pat<(i32 (vector_extract v4i32:$S, 0)),
(i32 (EXTRACT_SUBREG (VEXTUWLX (LI8 0), $S), sub_32))>;
// For extracting BE word 1, MFVSRWZ is better than VEXTUWLX
def : Pat<(i32 (vector_extract v4i32:$S, 1)),
(i32 VectorExtractions.LE_WORD_2)>;
def : Pat<(i32 (vector_extract v4i32:$S, 2)),
(i32 (EXTRACT_SUBREG (VEXTUWLX (LI8 8), $S), sub_32))>;
def : Pat<(i32 (vector_extract v4i32:$S, 3)),
(i32 (EXTRACT_SUBREG (VEXTUWLX (LI8 12), $S), sub_32))>;
}
let Predicates = [IsLittleEndian, HasDirectMove] in {
// v16i8 scalar <-> vector conversions (LE)
def : Pat<(v16i8 (scalar_to_vector i32:$A)),
(v16i8 (COPY_TO_REGCLASS MovesToVSR.LE_WORD_0, VSRC))>;
def : Pat<(v8i16 (scalar_to_vector i32:$A)),
(v8i16 (COPY_TO_REGCLASS MovesToVSR.LE_WORD_0, VSRC))>;
def : Pat<(v4i32 (scalar_to_vector i32:$A)),
(v4i32 MovesToVSR.LE_WORD_0)>;
def : Pat<(v2i64 (scalar_to_vector i64:$A)),
(v2i64 MovesToVSR.LE_DWORD_0)>;
// v2i64 scalar <-> vector conversions (LE)
def : Pat<(i64 (vector_extract v2i64:$S, 0)),
(i64 VectorExtractions.LE_DWORD_0)>;
def : Pat<(i64 (vector_extract v2i64:$S, 1)),
(i64 VectorExtractions.LE_DWORD_1)>;
def : Pat<(i64 (vector_extract v2i64:$S, i64:$Idx)),
(i64 VectorExtractions.LE_VARIABLE_DWORD)>;
} // IsLittleEndian, HasDirectMove
let Predicates = [IsLittleEndian, HasDirectMove, NoP9Altivec] in {
def : Pat<(i32 (vector_extract v16i8:$S, 0)),
(i32 VectorExtractions.LE_BYTE_0)>;
def : Pat<(i32 (vector_extract v16i8:$S, 1)),
(i32 VectorExtractions.LE_BYTE_1)>;
def : Pat<(i32 (vector_extract v16i8:$S, 2)),
(i32 VectorExtractions.LE_BYTE_2)>;
def : Pat<(i32 (vector_extract v16i8:$S, 3)),
(i32 VectorExtractions.LE_BYTE_3)>;
def : Pat<(i32 (vector_extract v16i8:$S, 4)),
(i32 VectorExtractions.LE_BYTE_4)>;
def : Pat<(i32 (vector_extract v16i8:$S, 5)),
(i32 VectorExtractions.LE_BYTE_5)>;
def : Pat<(i32 (vector_extract v16i8:$S, 6)),
(i32 VectorExtractions.LE_BYTE_6)>;
def : Pat<(i32 (vector_extract v16i8:$S, 7)),
(i32 VectorExtractions.LE_BYTE_7)>;
def : Pat<(i32 (vector_extract v16i8:$S, 8)),
(i32 VectorExtractions.LE_BYTE_8)>;
def : Pat<(i32 (vector_extract v16i8:$S, 9)),
(i32 VectorExtractions.LE_BYTE_9)>;
def : Pat<(i32 (vector_extract v16i8:$S, 10)),
(i32 VectorExtractions.LE_BYTE_10)>;
def : Pat<(i32 (vector_extract v16i8:$S, 11)),
(i32 VectorExtractions.LE_BYTE_11)>;
def : Pat<(i32 (vector_extract v16i8:$S, 12)),
(i32 VectorExtractions.LE_BYTE_12)>;
def : Pat<(i32 (vector_extract v16i8:$S, 13)),
(i32 VectorExtractions.LE_BYTE_13)>;
def : Pat<(i32 (vector_extract v16i8:$S, 14)),
(i32 VectorExtractions.LE_BYTE_14)>;
def : Pat<(i32 (vector_extract v16i8:$S, 15)),
(i32 VectorExtractions.LE_BYTE_15)>;
def : Pat<(i32 (vector_extract v16i8:$S, i64:$Idx)),
(i32 VectorExtractions.LE_VARIABLE_BYTE)>;
// v8i16 scalar <-> vector conversions (LE)
def : Pat<(i32 (vector_extract v8i16:$S, 0)),
(i32 VectorExtractions.LE_HALF_0)>;
def : Pat<(i32 (vector_extract v8i16:$S, 1)),
(i32 VectorExtractions.LE_HALF_1)>;
def : Pat<(i32 (vector_extract v8i16:$S, 2)),
(i32 VectorExtractions.LE_HALF_2)>;
def : Pat<(i32 (vector_extract v8i16:$S, 3)),
(i32 VectorExtractions.LE_HALF_3)>;
def : Pat<(i32 (vector_extract v8i16:$S, 4)),
(i32 VectorExtractions.LE_HALF_4)>;
def : Pat<(i32 (vector_extract v8i16:$S, 5)),
(i32 VectorExtractions.LE_HALF_5)>;
def : Pat<(i32 (vector_extract v8i16:$S, 6)),
(i32 VectorExtractions.LE_HALF_6)>;
def : Pat<(i32 (vector_extract v8i16:$S, 7)),
(i32 VectorExtractions.LE_HALF_7)>;
def : Pat<(i32 (vector_extract v8i16:$S, i64:$Idx)),
(i32 VectorExtractions.LE_VARIABLE_HALF)>;
// v4i32 scalar <-> vector conversions (LE)
def : Pat<(i32 (vector_extract v4i32:$S, 0)),
(i32 VectorExtractions.LE_WORD_0)>;
def : Pat<(i32 (vector_extract v4i32:$S, 1)),
(i32 VectorExtractions.LE_WORD_1)>;
def : Pat<(i32 (vector_extract v4i32:$S, 2)),
(i32 VectorExtractions.LE_WORD_2)>;
def : Pat<(i32 (vector_extract v4i32:$S, 3)),
(i32 VectorExtractions.LE_WORD_3)>;
def : Pat<(i32 (vector_extract v4i32:$S, i64:$Idx)),
(i32 VectorExtractions.LE_VARIABLE_WORD)>;
} // IsLittleEndian, HasDirectMove, NoP9Altivec
let Predicates = [HasDirectMove, HasVSX] in {
// bitconvert f32 -> i32
// (convert to 32-bit fp single, shift right 1 word, move to GPR)
def : Pat<(i32 (bitconvert f32:$S)),
(i32 (MFVSRWZ (EXTRACT_SUBREG
(XXSLDWI (XSCVDPSPN $S), (XSCVDPSPN $S), 3),
sub_64)))>;
// bitconvert i32 -> f32
// (move to FPR, shift left 1 word, convert to 64-bit fp single)
def : Pat<(f32 (bitconvert i32:$A)),
(f32 (XSCVSPDPN
(XXSLDWI MovesToVSR.LE_WORD_1, MovesToVSR.LE_WORD_1, 1)))>;
// bitconvert f64 -> i64
// (move to GPR, nothing else needed)
def : Pat<(i64 (bitconvert f64:$S)),
(i64 (MFVSRD $S))>;
// bitconvert i64 -> f64
// (move to FPR, nothing else needed)
def : Pat<(f64 (bitconvert i64:$S)),
(f64 (MTVSRD $S))>;
}
// Materialize a zero-vector of long long
def : Pat<(v2i64 immAllZerosV),
(v2i64 (XXLXORz))>;
}
def AlignValues {
dag F32_TO_BE_WORD1 = (v4f32 (XXSLDWI (XSCVDPSPN $B), (XSCVDPSPN $B), 3));
dag I32_TO_BE_WORD1 = (COPY_TO_REGCLASS (MTVSRWZ $B), VSRC);
}
// The following VSX instructions were introduced in Power ISA 3.0
def HasP9Vector : Predicate<"PPCSubTarget->hasP9Vector()">;
let AddedComplexity = 400, Predicates = [HasP9Vector] in {
// [PO VRT XO VRB XO /]
class X_VT5_XO5_VB5<bits<6> opcode, bits<5> xo2, bits<10> xo, string opc,
list<dag> pattern>
: X_RD5_XO5_RS5<opcode, xo2, xo, (outs vrrc:$vT), (ins vrrc:$vB),
!strconcat(opc, " $vT, $vB"), IIC_VecFP, pattern>;
// [PO VRT XO VRB XO RO], Round to Odd version of [PO VRT XO VRB XO /]
class X_VT5_XO5_VB5_Ro<bits<6> opcode, bits<5> xo2, bits<10> xo, string opc,
list<dag> pattern>
: X_VT5_XO5_VB5<opcode, xo2, xo, opc, pattern>, isDOT;
// [PO VRT XO VRB XO /], but the VRB is only used the left 64 bits (or less),
// So we use different operand class for VRB
class X_VT5_XO5_VB5_TyVB<bits<6> opcode, bits<5> xo2, bits<10> xo, string opc,
RegisterOperand vbtype, list<dag> pattern>
: X_RD5_XO5_RS5<opcode, xo2, xo, (outs vrrc:$vT), (ins vbtype:$vB),
!strconcat(opc, " $vT, $vB"), IIC_VecFP, pattern>;
// [PO VRT XO VRB XO /]
class X_VT5_XO5_VB5_VSFR<bits<6> opcode, bits<5> xo2, bits<10> xo, string opc,
list<dag> pattern>
: X_RD5_XO5_RS5<opcode, xo2, xo, (outs vfrc:$vT), (ins vrrc:$vB),
!strconcat(opc, " $vT, $vB"), IIC_VecFP, pattern>;
// [PO VRT XO VRB XO RO], Round to Odd version of [PO VRT XO VRB XO /]
class X_VT5_XO5_VB5_VSFR_Ro<bits<6> opcode, bits<5> xo2, bits<10> xo, string opc,
list<dag> pattern>
: X_VT5_XO5_VB5_VSFR<opcode, xo2, xo, opc, pattern>, isDOT;
// [PO T XO B XO BX /]
class XX2_RT5_XO5_XB6<bits<6> opcode, bits<5> xo2, bits<9> xo, string opc,
list<dag> pattern>
: XX2_RD5_XO5_RS6<opcode, xo2, xo, (outs g8rc:$rT), (ins vsfrc:$XB),
!strconcat(opc, " $rT, $XB"), IIC_VecFP, pattern>;
// [PO T XO B XO BX TX]
class XX2_XT6_XO5_XB6<bits<6> opcode, bits<5> xo2, bits<9> xo, string opc,
RegisterOperand vtype, list<dag> pattern>
: XX2_RD6_XO5_RS6<opcode, xo2, xo, (outs vtype:$XT), (ins vtype:$XB),
!strconcat(opc, " $XT, $XB"), IIC_VecFP, pattern>;
// [PO T A B XO AX BX TX], src and dest register use different operand class
class XX3_XT5_XA5_XB5<bits<6> opcode, bits<8> xo, string opc,
RegisterOperand xty, RegisterOperand aty, RegisterOperand bty,
InstrItinClass itin, list<dag> pattern>
: XX3Form<opcode, xo, (outs xty:$XT), (ins aty:$XA, bty:$XB),
!strconcat(opc, " $XT, $XA, $XB"), itin, pattern>;
// [PO VRT VRA VRB XO /]
class X_VT5_VA5_VB5<bits<6> opcode, bits<10> xo, string opc,
list<dag> pattern>
: XForm_1<opcode, xo, (outs vrrc:$vT), (ins vrrc:$vA, vrrc:$vB),
!strconcat(opc, " $vT, $vA, $vB"), IIC_VecFP, pattern>;
// [PO VRT VRA VRB XO RO], Round to Odd version of [PO VRT VRA VRB XO /]
class X_VT5_VA5_VB5_Ro<bits<6> opcode, bits<10> xo, string opc,
list<dag> pattern>
: X_VT5_VA5_VB5<opcode, xo, opc, pattern>, isDOT;
// [PO VRT VRA VRB XO /]
class X_VT5_VA5_VB5_FMA<bits<6> opcode, bits<10> xo, string opc,
list<dag> pattern>
: XForm_1<opcode, xo, (outs vrrc:$vT), (ins vrrc:$vTi, vrrc:$vA, vrrc:$vB),
!strconcat(opc, " $vT, $vA, $vB"), IIC_VecFP, pattern>,
RegConstraint<"$vTi = $vT">, NoEncode<"$vTi">;
// [PO VRT VRA VRB XO RO], Round to Odd version of [PO VRT VRA VRB XO /]
class X_VT5_VA5_VB5_FMA_Ro<bits<6> opcode, bits<10> xo, string opc,
list<dag> pattern>
: X_VT5_VA5_VB5_FMA<opcode, xo, opc, pattern>, isDOT;
//===--------------------------------------------------------------------===//
// Quad-Precision Scalar Move Instructions:
// Copy Sign
def XSCPSGNQP : X_VT5_VA5_VB5<63, 100, "xscpsgnqp",
[(set f128:$vT,
(fcopysign f128:$vB, f128:$vA))]>;
// Absolute/Negative-Absolute/Negate
def XSABSQP : X_VT5_XO5_VB5<63, 0, 804, "xsabsqp",
[(set f128:$vT, (fabs f128:$vB))]>;
def XSNABSQP : X_VT5_XO5_VB5<63, 8, 804, "xsnabsqp",
[(set f128:$vT, (fneg (fabs f128:$vB)))]>;
def XSNEGQP : X_VT5_XO5_VB5<63, 16, 804, "xsnegqp",
[(set f128:$vT, (fneg f128:$vB))]>;
//===--------------------------------------------------------------------===//
// Quad-Precision Scalar Floating-Point Arithmetic Instructions:
// Add/Divide/Multiply/Subtract
let isCommutable = 1 in {
def XSADDQP : X_VT5_VA5_VB5 <63, 4, "xsaddqp",
[(set f128:$vT, (fadd f128:$vA, f128:$vB))]>;
def XSMULQP : X_VT5_VA5_VB5 <63, 36, "xsmulqp",
[(set f128:$vT, (fmul f128:$vA, f128:$vB))]>;
}
def XSSUBQP : X_VT5_VA5_VB5 <63, 516, "xssubqp" ,
[(set f128:$vT, (fsub f128:$vA, f128:$vB))]>;
def XSDIVQP : X_VT5_VA5_VB5 <63, 548, "xsdivqp",
[(set f128:$vT, (fdiv f128:$vA, f128:$vB))]>;
// Square-Root
def XSSQRTQP : X_VT5_XO5_VB5 <63, 27, 804, "xssqrtqp",
[(set f128:$vT, (fsqrt f128:$vB))]>;
// (Negative) Multiply-{Add/Subtract}
def XSMADDQP : X_VT5_VA5_VB5_FMA <63, 388, "xsmaddqp",
[(set f128:$vT,
(fma f128:$vA, f128:$vB,
f128:$vTi))]>;
def XSMSUBQP : X_VT5_VA5_VB5_FMA <63, 420, "xsmsubqp" ,
[(set f128:$vT,
(fma f128:$vA, f128:$vB,
(fneg f128:$vTi)))]>;
def XSNMADDQP : X_VT5_VA5_VB5_FMA <63, 452, "xsnmaddqp",
[(set f128:$vT,
(fneg (fma f128:$vA, f128:$vB,
f128:$vTi)))]>;
def XSNMSUBQP : X_VT5_VA5_VB5_FMA <63, 484, "xsnmsubqp",
[(set f128:$vT,
(fneg (fma f128:$vA, f128:$vB,
(fneg f128:$vTi))))]>;
let isCommutable = 1 in {
def XSADDQPO : X_VT5_VA5_VB5_Ro<63, 4, "xsaddqpo",
[(set f128:$vT,
(int_ppc_addf128_round_to_odd
f128:$vA, f128:$vB))]>;
def XSMULQPO : X_VT5_VA5_VB5_Ro<63, 36, "xsmulqpo",
[(set f128:$vT,
(int_ppc_mulf128_round_to_odd
f128:$vA, f128:$vB))]>;
}
def XSSUBQPO : X_VT5_VA5_VB5_Ro<63, 516, "xssubqpo",
[(set f128:$vT,
(int_ppc_subf128_round_to_odd
f128:$vA, f128:$vB))]>;
def XSDIVQPO : X_VT5_VA5_VB5_Ro<63, 548, "xsdivqpo",
[(set f128:$vT,
(int_ppc_divf128_round_to_odd
f128:$vA, f128:$vB))]>;
def XSSQRTQPO : X_VT5_XO5_VB5_Ro<63, 27, 804, "xssqrtqpo",
[(set f128:$vT,
(int_ppc_sqrtf128_round_to_odd f128:$vB))]>;
def XSMADDQPO : X_VT5_VA5_VB5_FMA_Ro<63, 388, "xsmaddqpo",
[(set f128:$vT,
(int_ppc_fmaf128_round_to_odd
f128:$vA,f128:$vB,f128:$vTi))]>;
def XSMSUBQPO : X_VT5_VA5_VB5_FMA_Ro<63, 420, "xsmsubqpo" ,
[(set f128:$vT,
(int_ppc_fmaf128_round_to_odd
f128:$vA, f128:$vB, (fneg f128:$vTi)))]>;
def XSNMADDQPO: X_VT5_VA5_VB5_FMA_Ro<63, 452, "xsnmaddqpo",
[(set f128:$vT,
(fneg (int_ppc_fmaf128_round_to_odd
f128:$vA, f128:$vB, f128:$vTi)))]>;
def XSNMSUBQPO: X_VT5_VA5_VB5_FMA_Ro<63, 484, "xsnmsubqpo",
[(set f128:$vT,
(fneg (int_ppc_fmaf128_round_to_odd
f128:$vA, f128:$vB, (fneg f128:$vTi))))]>;
// Additional fnmsub patterns: -a*b + c == -(a*b - c)
def : Pat<(fma (fneg f128:$A), f128:$B, f128:$C), (XSNMSUBQP $C, $A, $B)>;
def : Pat<(fma f128:$A, (fneg f128:$B), f128:$C), (XSNMSUBQP $C, $A, $B)>;
//===--------------------------------------------------------------------===//
// Quad/Double-Precision Compare Instructions:
// [PO BF // VRA VRB XO /]
class X_BF3_VA5_VB5<bits<6> opcode, bits<10> xo, string opc,
list<dag> pattern>
: XForm_17<opcode, xo, (outs crrc:$crD), (ins vrrc:$VA, vrrc:$VB),
!strconcat(opc, " $crD, $VA, $VB"), IIC_FPCompare> {
let Pattern = pattern;
}
// QP Compare Ordered/Unordered
def XSCMPOQP : X_BF3_VA5_VB5<63, 132, "xscmpoqp", []>;
def XSCMPUQP : X_BF3_VA5_VB5<63, 644, "xscmpuqp", []>;
// DP/QP Compare Exponents
def XSCMPEXPDP : XX3Form_1<60, 59,
(outs crrc:$crD), (ins vsfrc:$XA, vsfrc:$XB),
"xscmpexpdp $crD, $XA, $XB", IIC_FPCompare, []>;
def XSCMPEXPQP : X_BF3_VA5_VB5<63, 164, "xscmpexpqp", []>;
// DP Compare ==, >=, >, !=
// Use vsrc for XT, because the entire register of XT is set.
// XT.dword[1] = 0x0000_0000_0000_0000
def XSCMPEQDP : XX3_XT5_XA5_XB5<60, 3, "xscmpeqdp", vsrc, vsfrc, vsfrc,
IIC_FPCompare, []>;
def XSCMPGEDP : XX3_XT5_XA5_XB5<60, 19, "xscmpgedp", vsrc, vsfrc, vsfrc,
IIC_FPCompare, []>;
def XSCMPGTDP : XX3_XT5_XA5_XB5<60, 11, "xscmpgtdp", vsrc, vsfrc, vsfrc,
IIC_FPCompare, []>;
//===--------------------------------------------------------------------===//
// Quad-Precision Floating-Point Conversion Instructions:
// Convert DP -> QP
def XSCVDPQP : X_VT5_XO5_VB5_TyVB<63, 22, 836, "xscvdpqp", vfrc,
[(set f128:$vT, (fpextend f64:$vB))]>;
// Round & Convert QP -> DP (dword[1] is set to zero)
def XSCVQPDP : X_VT5_XO5_VB5_VSFR<63, 20, 836, "xscvqpdp" , []>;
def XSCVQPDPO : X_VT5_XO5_VB5_VSFR_Ro<63, 20, 836, "xscvqpdpo",
[(set f64:$vT,
(int_ppc_truncf128_round_to_odd
f128:$vB))]>;
// Truncate & Convert QP -> (Un)Signed (D)Word (dword[1] is set to zero)
def XSCVQPSDZ : X_VT5_XO5_VB5<63, 25, 836, "xscvqpsdz", []>;
def XSCVQPSWZ : X_VT5_XO5_VB5<63, 9, 836, "xscvqpswz", []>;
def XSCVQPUDZ : X_VT5_XO5_VB5<63, 17, 836, "xscvqpudz", []>;
def XSCVQPUWZ : X_VT5_XO5_VB5<63, 1, 836, "xscvqpuwz", []>;
// Convert (Un)Signed DWord -> QP.
def XSCVSDQP : X_VT5_XO5_VB5_TyVB<63, 10, 836, "xscvsdqp", vfrc, []>;
def : Pat<(f128 (sint_to_fp i64:$src)),
(f128 (XSCVSDQP (COPY_TO_REGCLASS $src, VFRC)))>;
def : Pat<(f128 (sint_to_fp (i64 (PPCmfvsr f64:$src)))),
(f128 (XSCVSDQP $src))>;
def : Pat<(f128 (sint_to_fp (i32 (PPCmfvsr f64:$src)))),
(f128 (XSCVSDQP (VEXTSW2Ds $src)))>;
def XSCVUDQP : X_VT5_XO5_VB5_TyVB<63, 2, 836, "xscvudqp", vfrc, []>;
def : Pat<(f128 (uint_to_fp i64:$src)),
(f128 (XSCVUDQP (COPY_TO_REGCLASS $src, VFRC)))>;
def : Pat<(f128 (uint_to_fp (i64 (PPCmfvsr f64:$src)))),
(f128 (XSCVUDQP $src))>;
// Convert (Un)Signed Word -> QP.
def : Pat<(f128 (sint_to_fp i32:$src)),
(f128 (XSCVSDQP (MTVSRWA $src)))>;
def : Pat<(f128 (sint_to_fp (i32 (load xoaddr:$src)))),
(f128 (XSCVSDQP (LIWAX xoaddr:$src)))>;
def : Pat<(f128 (uint_to_fp i32:$src)),
(f128 (XSCVUDQP (MTVSRWZ $src)))>;
def : Pat<(f128 (uint_to_fp (i32 (load xoaddr:$src)))),
(f128 (XSCVUDQP (LIWZX xoaddr:$src)))>;
//===--------------------------------------------------------------------===//
// Round to Floating-Point Integer Instructions
// (Round &) Convert DP <-> HP
// Note! xscvdphp's src and dest register both use the left 64 bits, so we use
// vsfrc for src and dest register. xscvhpdp's src only use the left 16 bits,
// but we still use vsfrc for it.
def XSCVDPHP : XX2_XT6_XO5_XB6<60, 17, 347, "xscvdphp", vsfrc, []>;
def XSCVHPDP : XX2_XT6_XO5_XB6<60, 16, 347, "xscvhpdp", vsfrc, []>;
// Vector HP -> SP
def XVCVHPSP : XX2_XT6_XO5_XB6<60, 24, 475, "xvcvhpsp", vsrc, []>;
def XVCVSPHP : XX2_XT6_XO5_XB6<60, 25, 475, "xvcvsphp", vsrc,
[(set v4f32:$XT,
(int_ppc_vsx_xvcvsphp v4f32:$XB))]>;
// Pattern for matching Vector HP -> Vector SP intrinsic. Defined as a
// separate pattern so that it can convert the input register class from
// VRRC(v8i16) to VSRC.
def : Pat<(v4f32 (int_ppc_vsx_xvcvhpsp v8i16:$A)),
(v4f32 (XVCVHPSP (COPY_TO_REGCLASS $A, VSRC)))>;
class Z23_VT5_R1_VB5_RMC2_EX1<bits<6> opcode, bits<8> xo, bit ex, string opc,
list<dag> pattern>
: Z23Form_8<opcode, xo,
(outs vrrc:$vT), (ins u1imm:$r, vrrc:$vB, u2imm:$rmc),
!strconcat(opc, " $r, $vT, $vB, $rmc"), IIC_VecFP, pattern> {
let RC = ex;
}
// Round to Quad-Precision Integer [with Inexact]
def XSRQPI : Z23_VT5_R1_VB5_RMC2_EX1<63, 5, 0, "xsrqpi" , []>;
def XSRQPIX : Z23_VT5_R1_VB5_RMC2_EX1<63, 5, 1, "xsrqpix", []>;
// Use current rounding mode
def : Pat<(f128 (fnearbyint f128:$vB)), (f128 (XSRQPI 0, $vB, 3))>;
// Round to nearest, ties away from zero
def : Pat<(f128 (fround f128:$vB)), (f128 (XSRQPI 0, $vB, 0))>;
// Round towards Zero
def : Pat<(f128 (ftrunc f128:$vB)), (f128 (XSRQPI 1, $vB, 1))>;
// Round towards +Inf
def : Pat<(f128 (fceil f128:$vB)), (f128 (XSRQPI 1, $vB, 2))>;
// Round towards -Inf
def : Pat<(f128 (ffloor f128:$vB)), (f128 (XSRQPI 1, $vB, 3))>;
// Use current rounding mode, [with Inexact]
def : Pat<(f128 (frint f128:$vB)), (f128 (XSRQPIX 0, $vB, 3))>;
// Round Quad-Precision to Double-Extended Precision (fp80)
def XSRQPXP : Z23_VT5_R1_VB5_RMC2_EX1<63, 37, 0, "xsrqpxp", []>;
//===--------------------------------------------------------------------===//
// Insert/Extract Instructions
// Insert Exponent DP/QP
// XT NOTE: XT.dword[1] = 0xUUUU_UUUU_UUUU_UUUU
def XSIEXPDP : XX1Form <60, 918, (outs vsrc:$XT), (ins g8rc:$rA, g8rc:$rB),
"xsiexpdp $XT, $rA, $rB", IIC_VecFP, []>;
// vB NOTE: only vB.dword[0] is used, that's why we don't use
// X_VT5_VA5_VB5 form
def XSIEXPQP : XForm_18<63, 868, (outs vrrc:$vT), (ins vrrc:$vA, vsfrc:$vB),
"xsiexpqp $vT, $vA, $vB", IIC_VecFP, []>;
def : Pat<(f128 (int_ppc_scalar_insert_exp_qp f128:$vA, i64:$vB)),
(f128 (XSIEXPQP $vA, (MTVSRD $vB)))>;
// Extract Exponent/Significand DP/QP
def XSXEXPDP : XX2_RT5_XO5_XB6<60, 0, 347, "xsxexpdp", []>;
def XSXSIGDP : XX2_RT5_XO5_XB6<60, 1, 347, "xsxsigdp", []>;
def XSXEXPQP : X_VT5_XO5_VB5 <63, 2, 804, "xsxexpqp", []>;
def XSXSIGQP : X_VT5_XO5_VB5 <63, 18, 804, "xsxsigqp", []>;
def : Pat<(i64 (int_ppc_scalar_extract_expq f128:$vA)),
(i64 (MFVSRD (EXTRACT_SUBREG
(v2i64 (XSXEXPQP $vA)), sub_64)))>;
// Vector Insert Word
// XB NOTE: Only XB.dword[1] is used, but we use vsrc on XB.
def XXINSERTW :
XX2_RD6_UIM5_RS6<60, 181, (outs vsrc:$XT),
(ins vsrc:$XTi, vsrc:$XB, u4imm:$UIM),
"xxinsertw $XT, $XB, $UIM", IIC_VecFP,
[(set v4i32:$XT, (PPCvecinsert v4i32:$XTi, v4i32:$XB,
imm32SExt16:$UIM))]>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">;
// Vector Extract Unsigned Word
def XXEXTRACTUW : XX2_RD6_UIM5_RS6<60, 165,
(outs vsfrc:$XT), (ins vsrc:$XB, u4imm:$UIMM),
"xxextractuw $XT, $XB, $UIMM", IIC_VecFP, []>;
// Vector Insert Exponent DP/SP
def XVIEXPDP : XX3_XT5_XA5_XB5<60, 248, "xviexpdp", vsrc, vsrc, vsrc,
IIC_VecFP, [(set v2f64: $XT,(int_ppc_vsx_xviexpdp v2i64:$XA, v2i64:$XB))]>;
def XVIEXPSP : XX3_XT5_XA5_XB5<60, 216, "xviexpsp", vsrc, vsrc, vsrc,
IIC_VecFP, [(set v4f32: $XT,(int_ppc_vsx_xviexpsp v4i32:$XA, v4i32:$XB))]>;
// Vector Extract Exponent/Significand DP/SP
def XVXEXPDP : XX2_XT6_XO5_XB6<60, 0, 475, "xvxexpdp", vsrc,
[(set v2i64: $XT,
(int_ppc_vsx_xvxexpdp v2f64:$XB))]>;
def XVXEXPSP : XX2_XT6_XO5_XB6<60, 8, 475, "xvxexpsp", vsrc,
[(set v4i32: $XT,
(int_ppc_vsx_xvxexpsp v4f32:$XB))]>;
def XVXSIGDP : XX2_XT6_XO5_XB6<60, 1, 475, "xvxsigdp", vsrc,
[(set v2i64: $XT,
(int_ppc_vsx_xvxsigdp v2f64:$XB))]>;
def XVXSIGSP : XX2_XT6_XO5_XB6<60, 9, 475, "xvxsigsp", vsrc,
[(set v4i32: $XT,
(int_ppc_vsx_xvxsigsp v4f32:$XB))]>;
let AddedComplexity = 400, Predicates = [HasP9Vector] in {
// Extra patterns expanding to vector Extract Word/Insert Word
def : Pat<(v4i32 (int_ppc_vsx_xxinsertw v4i32:$A, v2i64:$B, imm:$IMM)),
(v4i32 (XXINSERTW $A, $B, imm:$IMM))>;
def : Pat<(v2i64 (int_ppc_vsx_xxextractuw v2i64:$A, imm:$IMM)),
(v2i64 (COPY_TO_REGCLASS (XXEXTRACTUW $A, imm:$IMM), VSRC))>;
} // AddedComplexity = 400, HasP9Vector
//===--------------------------------------------------------------------===//
// Test Data Class SP/DP/QP
def XSTSTDCSP : XX2_BF3_DCMX7_RS6<60, 298,
(outs crrc:$BF), (ins u7imm:$DCMX, vsfrc:$XB),
"xststdcsp $BF, $XB, $DCMX", IIC_VecFP, []>;
def XSTSTDCDP : XX2_BF3_DCMX7_RS6<60, 362,
(outs crrc:$BF), (ins u7imm:$DCMX, vsfrc:$XB),
"xststdcdp $BF, $XB, $DCMX", IIC_VecFP, []>;
def XSTSTDCQP : X_BF3_DCMX7_RS5 <63, 708,
(outs crrc:$BF), (ins u7imm:$DCMX, vrrc:$vB),
"xststdcqp $BF, $vB, $DCMX", IIC_VecFP, []>;
// Vector Test Data Class SP/DP
def XVTSTDCSP : XX2_RD6_DCMX7_RS6<60, 13, 5,
(outs vsrc:$XT), (ins u7imm:$DCMX, vsrc:$XB),
"xvtstdcsp $XT, $XB, $DCMX", IIC_VecFP,
[(set v4i32: $XT,
(int_ppc_vsx_xvtstdcsp v4f32:$XB, timm:$DCMX))]>;
def XVTSTDCDP : XX2_RD6_DCMX7_RS6<60, 15, 5,
(outs vsrc:$XT), (ins u7imm:$DCMX, vsrc:$XB),
"xvtstdcdp $XT, $XB, $DCMX", IIC_VecFP,
[(set v2i64: $XT,
(int_ppc_vsx_xvtstdcdp v2f64:$XB, timm:$DCMX))]>;
//===--------------------------------------------------------------------===//
// Maximum/Minimum Type-C/Type-J DP
def XSMAXCDP : XX3_XT5_XA5_XB5<60, 128, "xsmaxcdp", vsfrc, vsfrc, vsfrc,
IIC_VecFP,
[(set f64:$XT, (PPCxsmaxc f64:$XA, f64:$XB))]>;
def XSMAXJDP : XX3_XT5_XA5_XB5<60, 144, "xsmaxjdp", vsrc, vsfrc, vsfrc,
IIC_VecFP, []>;
def XSMINCDP : XX3_XT5_XA5_XB5<60, 136, "xsmincdp", vsfrc, vsfrc, vsfrc,
IIC_VecFP,
[(set f64:$XT, (PPCxsminc f64:$XA, f64:$XB))]>;
def XSMINJDP : XX3_XT5_XA5_XB5<60, 152, "xsminjdp", vsrc, vsfrc, vsfrc,
IIC_VecFP, []>;
//===--------------------------------------------------------------------===//
// Vector Byte-Reverse H/W/D/Q Word
def XXBRH : XX2_XT6_XO5_XB6<60, 7, 475, "xxbrh", vsrc, []>;
def XXBRW : XX2_XT6_XO5_XB6<60, 15, 475, "xxbrw", vsrc, []>;
def XXBRD : XX2_XT6_XO5_XB6<60, 23, 475, "xxbrd", vsrc, []>;
def XXBRQ : XX2_XT6_XO5_XB6<60, 31, 475, "xxbrq", vsrc, []>;
// Vector Reverse
def : Pat<(v8i16 (PPCxxreverse v8i16 :$A)),
(v8i16 (COPY_TO_REGCLASS (XXBRH (COPY_TO_REGCLASS $A, VSRC)), VRRC))>;
def : Pat<(v4i32 (PPCxxreverse v4i32 :$A)),
(v4i32 (XXBRW $A))>;
def : Pat<(v2i64 (PPCxxreverse v2i64 :$A)),
(v2i64 (XXBRD $A))>;
def : Pat<(v1i128 (PPCxxreverse v1i128 :$A)),
(v1i128 (COPY_TO_REGCLASS (XXBRQ (COPY_TO_REGCLASS $A, VSRC)), VRRC))>;
// Vector Permute
def XXPERM : XX3_XT5_XA5_XB5<60, 26, "xxperm" , vsrc, vsrc, vsrc,
IIC_VecPerm, []>;
def XXPERMR : XX3_XT5_XA5_XB5<60, 58, "xxpermr", vsrc, vsrc, vsrc,
IIC_VecPerm, []>;
// Vector Splat Immediate Byte
def XXSPLTIB : X_RD6_IMM8<60, 360, (outs vsrc:$XT), (ins u8imm:$IMM8),
"xxspltib $XT, $IMM8", IIC_VecPerm, []>;
//===--------------------------------------------------------------------===//
// Vector/Scalar Load/Store Instructions
// When adding new D-Form loads/stores, be sure to update the ImmToIdxMap in
// PPCRegisterInfo::PPCRegisterInfo and maybe save yourself some debugging.
let mayLoad = 1, mayStore = 0 in {
// Load Vector
def LXV : DQ_RD6_RS5_DQ12<61, 1, (outs vsrc:$XT), (ins memrix16:$src),
"lxv $XT, $src", IIC_LdStLFD, []>;
// Load DWord
def LXSD : DSForm_1<57, 2, (outs vfrc:$vD), (ins memrix:$src),
"lxsd $vD, $src", IIC_LdStLFD, []>;
// Load SP from src, convert it to DP, and place in dword[0]
def LXSSP : DSForm_1<57, 3, (outs vfrc:$vD), (ins memrix:$src),
"lxssp $vD, $src", IIC_LdStLFD, []>;
// [PO T RA RB XO TX] almost equal to [PO S RA RB XO SX], but has different
// "out" and "in" dag
class X_XT6_RA5_RB5<bits<6> opcode, bits<10> xo, string opc,
RegisterOperand vtype, list<dag> pattern>
: XX1Form_memOp<opcode, xo, (outs vtype:$XT), (ins memrr:$src),
!strconcat(opc, " $XT, $src"), IIC_LdStLFD, pattern>;
// Load as Integer Byte/Halfword & Zero Indexed
def LXSIBZX : X_XT6_RA5_RB5<31, 781, "lxsibzx", vsfrc,
[(set f64:$XT, (PPClxsizx xoaddr:$src, 1))]>;
def LXSIHZX : X_XT6_RA5_RB5<31, 813, "lxsihzx", vsfrc,
[(set f64:$XT, (PPClxsizx xoaddr:$src, 2))]>;
// Load Vector Halfword*8/Byte*16 Indexed
def LXVH8X : X_XT6_RA5_RB5<31, 812, "lxvh8x" , vsrc, []>;
def LXVB16X : X_XT6_RA5_RB5<31, 876, "lxvb16x", vsrc, []>;
// Load Vector Indexed
def LXVX : X_XT6_RA5_RB5<31, 268, "lxvx" , vsrc,
[(set v2f64:$XT, (load xaddrX16:$src))]>;
// Load Vector (Left-justified) with Length
def LXVL : XX1Form_memOp<31, 269, (outs vsrc:$XT), (ins memr:$src, g8rc:$rB),
"lxvl $XT, $src, $rB", IIC_LdStLoad,
[(set v4i32:$XT, (int_ppc_vsx_lxvl addr:$src, i64:$rB))]>;
def LXVLL : XX1Form_memOp<31,301, (outs vsrc:$XT), (ins memr:$src, g8rc:$rB),
"lxvll $XT, $src, $rB", IIC_LdStLoad,
[(set v4i32:$XT, (int_ppc_vsx_lxvll addr:$src, i64:$rB))]>;
// Load Vector Word & Splat Indexed
def LXVWSX : X_XT6_RA5_RB5<31, 364, "lxvwsx" , vsrc, []>;
} // mayLoad
// When adding new D-Form loads/stores, be sure to update the ImmToIdxMap in
// PPCRegisterInfo::PPCRegisterInfo and maybe save yourself some debugging.
let mayStore = 1, mayLoad = 0 in {
// Store Vector
def STXV : DQ_RD6_RS5_DQ12<61, 5, (outs), (ins vsrc:$XT, memrix16:$dst),
"stxv $XT, $dst", IIC_LdStSTFD, []>;
// Store DWord
def STXSD : DSForm_1<61, 2, (outs), (ins vfrc:$vS, memrix:$dst),
"stxsd $vS, $dst", IIC_LdStSTFD, []>;
// Convert DP of dword[0] to SP, and Store to dst
def STXSSP : DSForm_1<61, 3, (outs), (ins vfrc:$vS, memrix:$dst),
"stxssp $vS, $dst", IIC_LdStSTFD, []>;
// [PO S RA RB XO SX]
class X_XS6_RA5_RB5<bits<6> opcode, bits<10> xo, string opc,
RegisterOperand vtype, list<dag> pattern>
: XX1Form_memOp<opcode, xo, (outs), (ins vtype:$XT, memrr:$dst),
!strconcat(opc, " $XT, $dst"), IIC_LdStSTFD, pattern>;
// Store as Integer Byte/Halfword Indexed
def STXSIBX : X_XS6_RA5_RB5<31, 909, "stxsibx" , vsfrc,
[(PPCstxsix f64:$XT, xoaddr:$dst, 1)]>;
def STXSIHX : X_XS6_RA5_RB5<31, 941, "stxsihx" , vsfrc,
[(PPCstxsix f64:$XT, xoaddr:$dst, 2)]>;
let isCodeGenOnly = 1 in {
def STXSIBXv : X_XS6_RA5_RB5<31, 909, "stxsibx" , vsrc, []>;
def STXSIHXv : X_XS6_RA5_RB5<31, 941, "stxsihx" , vsrc, []>;
}
// Store Vector Halfword*8/Byte*16 Indexed
def STXVH8X : X_XS6_RA5_RB5<31, 940, "stxvh8x" , vsrc, []>;
def STXVB16X : X_XS6_RA5_RB5<31, 1004, "stxvb16x", vsrc, []>;
// Store Vector Indexed
def STXVX : X_XS6_RA5_RB5<31, 396, "stxvx" , vsrc,
[(store v2f64:$XT, xaddrX16:$dst)]>;
// Store Vector (Left-justified) with Length
def STXVL : XX1Form_memOp<31, 397, (outs),
(ins vsrc:$XT, memr:$dst, g8rc:$rB),
"stxvl $XT, $dst, $rB", IIC_LdStLoad,
[(int_ppc_vsx_stxvl v4i32:$XT, addr:$dst,
i64:$rB)]>;
def STXVLL : XX1Form_memOp<31, 429, (outs),
(ins vsrc:$XT, memr:$dst, g8rc:$rB),
"stxvll $XT, $dst, $rB", IIC_LdStLoad,
[(int_ppc_vsx_stxvll v4i32:$XT, addr:$dst,
i64:$rB)]>;
} // mayStore
let Predicates = [IsLittleEndian] in {
def: Pat<(f32 (PPCfcfids (f64 (PPCmtvsra (i32 (extractelt v4i32:$A, 0)))))),
(f32 (XSCVSPDPN (XVCVSXWSP (XXSPLTW $A, 3))))>;
def: Pat<(f32 (PPCfcfids (f64 (PPCmtvsra (i32 (extractelt v4i32:$A, 1)))))),
(f32 (XSCVSPDPN (XVCVSXWSP (XXSPLTW $A, 2))))>;
def: Pat<(f32 (PPCfcfids (f64 (PPCmtvsra (i32 (extractelt v4i32:$A, 2)))))),
(f32 (XSCVSPDPN (XVCVSXWSP (XXSPLTW $A, 1))))>;
def: Pat<(f32 (PPCfcfids (f64 (PPCmtvsra (i32 (extractelt v4i32:$A, 3)))))),
(f32 (XSCVSPDPN (XVCVSXWSP (XXSPLTW $A, 0))))>;
def: Pat<(f64 (PPCfcfid (f64 (PPCmtvsra (i32 (extractelt v4i32:$A, 0)))))),
(f64 (COPY_TO_REGCLASS (XVCVSXWDP (XXSPLTW $A, 3)), VSFRC))>;
def: Pat<(f64 (PPCfcfid (f64 (PPCmtvsra (i32 (extractelt v4i32:$A, 1)))))),
(f64 (COPY_TO_REGCLASS (XVCVSXWDP (XXSPLTW $A, 2)), VSFRC))>;
def: Pat<(f64 (PPCfcfid (f64 (PPCmtvsra (i32 (extractelt v4i32:$A, 2)))))),
(f64 (COPY_TO_REGCLASS (XVCVSXWDP (XXSPLTW $A, 1)), VSFRC))>;
def: Pat<(f64 (PPCfcfid (f64 (PPCmtvsra (i32 (extractelt v4i32:$A, 3)))))),
(f64 (COPY_TO_REGCLASS (XVCVSXWDP (XXSPLTW $A, 0)), VSFRC))>;
}
let Predicates = [IsBigEndian] in {
def: Pat<(f32 (PPCfcfids (f64 (PPCmtvsra (i32 (extractelt v4i32:$A, 0)))))),
(f32 (XSCVSPDPN (XVCVSXWSP (XXSPLTW $A, 0))))>;
def: Pat<(f32 (PPCfcfids (f64 (PPCmtvsra (i32 (extractelt v4i32:$A, 1)))))),
(f32 (XSCVSPDPN (XVCVSXWSP (XXSPLTW $A, 1))))>;
def: Pat<(f32 (PPCfcfids (f64 (PPCmtvsra (i32 (extractelt v4i32:$A, 2)))))),
(f32 (XSCVSPDPN (XVCVSXWSP (XXSPLTW $A, 2))))>;
def: Pat<(f32 (PPCfcfids (f64 (PPCmtvsra (i32 (extractelt v4i32:$A, 3)))))),
(f32 (XSCVSPDPN (XVCVSXWSP (XXSPLTW $A, 3))))>;
def: Pat<(f64 (PPCfcfid (f64 (PPCmtvsra (i32 (extractelt v4i32:$A, 0)))))),
(f64 (COPY_TO_REGCLASS (XVCVSXWDP (XXSPLTW $A, 0)), VSFRC))>;
def: Pat<(f64 (PPCfcfid (f64 (PPCmtvsra (i32 (extractelt v4i32:$A, 1)))))),
(f64 (COPY_TO_REGCLASS (XVCVSXWDP (XXSPLTW $A, 1)), VSFRC))>;
def: Pat<(f64 (PPCfcfid (f64 (PPCmtvsra (i32 (extractelt v4i32:$A, 2)))))),
(f64 (COPY_TO_REGCLASS (XVCVSXWDP (XXSPLTW $A, 2)), VSFRC))>;
def: Pat<(f64 (PPCfcfid (f64 (PPCmtvsra (i32 (extractelt v4i32:$A, 3)))))),
(f64 (COPY_TO_REGCLASS (XVCVSXWDP (XXSPLTW $A, 3)), VSFRC))>;
}
// Alternate patterns for PPCmtvsrz where the output is v8i16 or v16i8 instead
// of f64
def : Pat<(v8i16 (PPCmtvsrz i32:$A)),
(v8i16 (SUBREG_TO_REG (i64 1), (MTVSRWZ $A), sub_64))>;
def : Pat<(v16i8 (PPCmtvsrz i32:$A)),
(v16i8 (SUBREG_TO_REG (i64 1), (MTVSRWZ $A), sub_64))>;
// Patterns for which instructions from ISA 3.0 are a better match
let Predicates = [IsLittleEndian, HasP9Vector] in {
def : Pat<(f32 (PPCfcfidus (f64 (PPCmtvsrz (i32 (extractelt v4i32:$A, 0)))))),
(f32 (XSCVUXDSP (XXEXTRACTUW $A, 12)))>;
def : Pat<(f32 (PPCfcfidus (f64 (PPCmtvsrz (i32 (extractelt v4i32:$A, 1)))))),
(f32 (XSCVUXDSP (XXEXTRACTUW $A, 8)))>;
def : Pat<(f32 (PPCfcfidus (f64 (PPCmtvsrz (i32 (extractelt v4i32:$A, 2)))))),
(f32 (XSCVUXDSP (XXEXTRACTUW $A, 4)))>;
def : Pat<(f32 (PPCfcfidus (f64 (PPCmtvsrz (i32 (extractelt v4i32:$A, 3)))))),
(f32 (XSCVUXDSP (XXEXTRACTUW $A, 0)))>;
def : Pat<(f64 (PPCfcfidu (f64 (PPCmtvsrz (i32 (extractelt v4i32:$A, 0)))))),
(f64 (XSCVUXDDP (XXEXTRACTUW $A, 12)))>;
def : Pat<(f64 (PPCfcfidu (f64 (PPCmtvsrz (i32 (extractelt v4i32:$A, 1)))))),
(f64 (XSCVUXDDP (XXEXTRACTUW $A, 8)))>;
def : Pat<(f64 (PPCfcfidu (f64 (PPCmtvsrz (i32 (extractelt v4i32:$A, 2)))))),
(f64 (XSCVUXDDP (XXEXTRACTUW $A, 4)))>;
def : Pat<(f64 (PPCfcfidu (f64 (PPCmtvsrz (i32 (extractelt v4i32:$A, 3)))))),
(f64 (XSCVUXDDP (XXEXTRACTUW $A, 0)))>;
def : Pat<(v4i32 (insertelt v4i32:$A, i32:$B, 0)),
(v4i32 (XXINSERTW v4i32:$A, AlignValues.I32_TO_BE_WORD1, 12))>;
def : Pat<(v4i32 (insertelt v4i32:$A, i32:$B, 1)),
(v4i32 (XXINSERTW v4i32:$A, AlignValues.I32_TO_BE_WORD1, 8))>;
def : Pat<(v4i32 (insertelt v4i32:$A, i32:$B, 2)),
(v4i32 (XXINSERTW v4i32:$A, AlignValues.I32_TO_BE_WORD1, 4))>;
def : Pat<(v4i32 (insertelt v4i32:$A, i32:$B, 3)),
(v4i32 (XXINSERTW v4i32:$A, AlignValues.I32_TO_BE_WORD1, 0))>;
def : Pat<(v4f32 (insertelt v4f32:$A, f32:$B, 0)),
(v4f32 (XXINSERTW v4f32:$A, AlignValues.F32_TO_BE_WORD1, 12))>;
def : Pat<(v4f32 (insertelt v4f32:$A, f32:$B, 1)),
(v4f32 (XXINSERTW v4f32:$A, AlignValues.F32_TO_BE_WORD1, 8))>;
def : Pat<(v4f32 (insertelt v4f32:$A, f32:$B, 2)),
(v4f32 (XXINSERTW v4f32:$A, AlignValues.F32_TO_BE_WORD1, 4))>;
def : Pat<(v4f32 (insertelt v4f32:$A, f32:$B, 3)),
(v4f32 (XXINSERTW v4f32:$A, AlignValues.F32_TO_BE_WORD1, 0))>;
def : Pat<(v8i16 (PPCld_vec_be xoaddr:$src)),
(COPY_TO_REGCLASS (LXVH8X xoaddr:$src), VRRC)>;
def : Pat<(PPCst_vec_be v8i16:$rS, xoaddr:$dst),
(STXVH8X (COPY_TO_REGCLASS $rS, VSRC), xoaddr:$dst)>;
def : Pat<(v16i8 (PPCld_vec_be xoaddr:$src)),
(COPY_TO_REGCLASS (LXVB16X xoaddr:$src), VRRC)>;
def : Pat<(PPCst_vec_be v16i8:$rS, xoaddr:$dst),
(STXVB16X (COPY_TO_REGCLASS $rS, VSRC), xoaddr:$dst)>;
} // IsLittleEndian, HasP9Vector
let Predicates = [IsBigEndian, HasP9Vector] in {
def : Pat<(f32 (PPCfcfidus (f64 (PPCmtvsrz (i32 (extractelt v4i32:$A, 0)))))),
(f32 (XSCVUXDSP (XXEXTRACTUW $A, 0)))>;
def : Pat<(f32 (PPCfcfidus (f64 (PPCmtvsrz (i32 (extractelt v4i32:$A, 1)))))),
(f32 (XSCVUXDSP (XXEXTRACTUW $A, 4)))>;
def : Pat<(f32 (PPCfcfidus (f64 (PPCmtvsrz (i32 (extractelt v4i32:$A, 2)))))),
(f32 (XSCVUXDSP (XXEXTRACTUW $A, 8)))>;
def : Pat<(f32 (PPCfcfidus (f64 (PPCmtvsrz (i32 (extractelt v4i32:$A, 3)))))),
(f32 (XSCVUXDSP (XXEXTRACTUW $A, 12)))>;
def : Pat<(f64 (PPCfcfidu (f64 (PPCmtvsrz (i32 (extractelt v4i32:$A, 0)))))),
(f64 (XSCVUXDDP (XXEXTRACTUW $A, 0)))>;
def : Pat<(f64 (PPCfcfidu (f64 (PPCmtvsrz (i32 (extractelt v4i32:$A, 1)))))),
(f64 (XSCVUXDDP (XXEXTRACTUW $A, 4)))>;
def : Pat<(f64 (PPCfcfidu (f64 (PPCmtvsrz (i32 (extractelt v4i32:$A, 2)))))),
(f64 (XSCVUXDDP (XXEXTRACTUW $A, 8)))>;
def : Pat<(f64 (PPCfcfidu (f64 (PPCmtvsrz (i32 (extractelt v4i32:$A, 3)))))),
(f64 (XSCVUXDDP (XXEXTRACTUW $A, 12)))>;
def : Pat<(v4i32 (insertelt v4i32:$A, i32:$B, 0)),
(v4i32 (XXINSERTW v4i32:$A, AlignValues.I32_TO_BE_WORD1, 0))>;
def : Pat<(v4i32 (insertelt v4i32:$A, i32:$B, 1)),
(v4i32 (XXINSERTW v4i32:$A, AlignValues.I32_TO_BE_WORD1, 4))>;
def : Pat<(v4i32 (insertelt v4i32:$A, i32:$B, 2)),
(v4i32 (XXINSERTW v4i32:$A, AlignValues.I32_TO_BE_WORD1, 8))>;
def : Pat<(v4i32 (insertelt v4i32:$A, i32:$B, 3)),
(v4i32 (XXINSERTW v4i32:$A, AlignValues.I32_TO_BE_WORD1, 12))>;
def : Pat<(v4f32 (insertelt v4f32:$A, f32:$B, 0)),
(v4f32 (XXINSERTW v4f32:$A, AlignValues.F32_TO_BE_WORD1, 0))>;
def : Pat<(v4f32 (insertelt v4f32:$A, f32:$B, 1)),
(v4f32 (XXINSERTW v4f32:$A, AlignValues.F32_TO_BE_WORD1, 4))>;
def : Pat<(v4f32 (insertelt v4f32:$A, f32:$B, 2)),
(v4f32 (XXINSERTW v4f32:$A, AlignValues.F32_TO_BE_WORD1, 8))>;
def : Pat<(v4f32 (insertelt v4f32:$A, f32:$B, 3)),
(v4f32 (XXINSERTW v4f32:$A, AlignValues.F32_TO_BE_WORD1, 12))>;
} // IsBigEndian, HasP9Vector
// D-Form Load/Store
def : Pat<(v4i32 (quadwOffsetLoad iaddrX16:$src)), (LXV memrix16:$src)>;
def : Pat<(v4f32 (quadwOffsetLoad iaddrX16:$src)), (LXV memrix16:$src)>;
def : Pat<(v2i64 (quadwOffsetLoad iaddrX16:$src)), (LXV memrix16:$src)>;
def : Pat<(v2f64 (quadwOffsetLoad iaddrX16:$src)), (LXV memrix16:$src)>;
def : Pat<(f128 (quadwOffsetLoad iaddrX16:$src)),
(COPY_TO_REGCLASS (LXV memrix16:$src), VRRC)>;
def : Pat<(v4i32 (int_ppc_vsx_lxvw4x iaddrX16:$src)), (LXV memrix16:$src)>;
def : Pat<(v2f64 (int_ppc_vsx_lxvd2x iaddrX16:$src)), (LXV memrix16:$src)>;
def : Pat<(quadwOffsetStore v4f32:$rS, iaddrX16:$dst), (STXV $rS, memrix16:$dst)>;
def : Pat<(quadwOffsetStore v4i32:$rS, iaddrX16:$dst), (STXV $rS, memrix16:$dst)>;
def : Pat<(quadwOffsetStore v2f64:$rS, iaddrX16:$dst), (STXV $rS, memrix16:$dst)>;
def : Pat<(quadwOffsetStore f128:$rS, iaddrX16:$dst),
(STXV (COPY_TO_REGCLASS $rS, VSRC), memrix16:$dst)>;
def : Pat<(quadwOffsetStore v2i64:$rS, iaddrX16:$dst), (STXV $rS, memrix16:$dst)>;
def : Pat<(int_ppc_vsx_stxvw4x v4i32:$rS, iaddrX16:$dst),
(STXV $rS, memrix16:$dst)>;
def : Pat<(int_ppc_vsx_stxvd2x v2f64:$rS, iaddrX16:$dst),
(STXV $rS, memrix16:$dst)>;
def : Pat<(v2f64 (nonQuadwOffsetLoad xoaddr:$src)), (LXVX xoaddr:$src)>;
def : Pat<(v2i64 (nonQuadwOffsetLoad xoaddr:$src)), (LXVX xoaddr:$src)>;
def : Pat<(v4f32 (nonQuadwOffsetLoad xoaddr:$src)), (LXVX xoaddr:$src)>;
def : Pat<(v4i32 (nonQuadwOffsetLoad xoaddr:$src)), (LXVX xoaddr:$src)>;
def : Pat<(v4i32 (int_ppc_vsx_lxvw4x xoaddr:$src)), (LXVX xoaddr:$src)>;
def : Pat<(v2f64 (int_ppc_vsx_lxvd2x xoaddr:$src)), (LXVX xoaddr:$src)>;
def : Pat<(f128 (nonQuadwOffsetLoad xoaddr:$src)),
(COPY_TO_REGCLASS (LXVX xoaddr:$src), VRRC)>;
def : Pat<(nonQuadwOffsetStore f128:$rS, xoaddr:$dst),
(STXVX (COPY_TO_REGCLASS $rS, VSRC), xoaddr:$dst)>;
def : Pat<(nonQuadwOffsetStore v2f64:$rS, xoaddr:$dst),
(STXVX $rS, xoaddr:$dst)>;
def : Pat<(nonQuadwOffsetStore v2i64:$rS, xoaddr:$dst),
(STXVX $rS, xoaddr:$dst)>;
def : Pat<(nonQuadwOffsetStore v4f32:$rS, xoaddr:$dst),
(STXVX $rS, xoaddr:$dst)>;
def : Pat<(nonQuadwOffsetStore v4i32:$rS, xoaddr:$dst),
(STXVX $rS, xoaddr:$dst)>;
def : Pat<(int_ppc_vsx_stxvw4x v4i32:$rS, xoaddr:$dst),
(STXVX $rS, xoaddr:$dst)>;
def : Pat<(int_ppc_vsx_stxvd2x v2f64:$rS, xoaddr:$dst),
(STXVX $rS, xoaddr:$dst)>;
let AddedComplexity = 400 in {
// LIWAX - This instruction is used for sign extending i32 -> i64.
// LIWZX - This instruction will be emitted for i32, f32, and when
// zero-extending i32 to i64 (zext i32 -> i64).
let Predicates = [IsLittleEndian] in {
def : Pat<(v2i64 (scalar_to_vector (i64 (sextloadi32 xoaddr:$src)))),
(v2i64 (XXPERMDIs
(COPY_TO_REGCLASS (LIWAX xoaddr:$src), VSRC), 2))>;
def : Pat<(v2i64 (scalar_to_vector (i64 (zextloadi32 xoaddr:$src)))),
(v2i64 (XXPERMDIs
(COPY_TO_REGCLASS (LIWZX xoaddr:$src), VSRC), 2))>;
def : Pat<(v4i32 (scalar_to_vector (i32 (load xoaddr:$src)))),
(v4i32 (XXPERMDIs
(COPY_TO_REGCLASS (LIWZX xoaddr:$src), VSRC), 2))>;
def : Pat<(v4f32 (scalar_to_vector (f32 (load xoaddr:$src)))),
(v4f32 (XXPERMDIs
(COPY_TO_REGCLASS (LIWZX xoaddr:$src), VSRC), 2))>;
}
let Predicates = [IsBigEndian] in {
def : Pat<(v2i64 (scalar_to_vector (i64 (sextloadi32 xoaddr:$src)))),
(v2i64 (COPY_TO_REGCLASS (LIWAX xoaddr:$src), VSRC))>;
def : Pat<(v2i64 (scalar_to_vector (i64 (zextloadi32 xoaddr:$src)))),
(v2i64 (COPY_TO_REGCLASS (LIWZX xoaddr:$src), VSRC))>;
def : Pat<(v4i32 (scalar_to_vector (i32 (load xoaddr:$src)))),
(v4i32 (XXSLDWIs
(COPY_TO_REGCLASS (LIWZX xoaddr:$src), VSRC), 1))>;
def : Pat<(v4f32 (scalar_to_vector (f32 (load xoaddr:$src)))),
(v4f32 (XXSLDWIs
(COPY_TO_REGCLASS (LIWZX xoaddr:$src), VSRC), 1))>;
}
}
// Build vectors from i8 loads
def : Pat<(v16i8 (scalar_to_vector ScalarLoads.Li8)),
(v16i8 (VSPLTBs 7, (LXSIBZX xoaddr:$src)))>;
def : Pat<(v8i16 (scalar_to_vector ScalarLoads.ZELi8)),
(v8i16 (VSPLTHs 3, (LXSIBZX xoaddr:$src)))>;
def : Pat<(v4i32 (scalar_to_vector ScalarLoads.ZELi8)),
(v4i32 (XXSPLTWs (LXSIBZX xoaddr:$src), 1))>;
def : Pat<(v2i64 (scalar_to_vector ScalarLoads.ZELi8i64)),
(v2i64 (XXPERMDIs (LXSIBZX xoaddr:$src), 0))>;
def : Pat<(v4i32 (scalar_to_vector ScalarLoads.SELi8)),
(v4i32 (XXSPLTWs (VEXTSB2Ws (LXSIBZX xoaddr:$src)), 1))>;
def : Pat<(v2i64 (scalar_to_vector ScalarLoads.SELi8i64)),
(v2i64 (XXPERMDIs (VEXTSB2Ds (LXSIBZX xoaddr:$src)), 0))>;
// Build vectors from i16 loads
def : Pat<(v8i16 (scalar_to_vector ScalarLoads.Li16)),
(v8i16 (VSPLTHs 3, (LXSIHZX xoaddr:$src)))>;
def : Pat<(v4i32 (scalar_to_vector ScalarLoads.ZELi16)),
(v4i32 (XXSPLTWs (LXSIHZX xoaddr:$src), 1))>;
def : Pat<(v2i64 (scalar_to_vector ScalarLoads.ZELi16i64)),
(v2i64 (XXPERMDIs (LXSIHZX xoaddr:$src), 0))>;
def : Pat<(v4i32 (scalar_to_vector ScalarLoads.SELi16)),
(v4i32 (XXSPLTWs (VEXTSH2Ws (LXSIHZX xoaddr:$src)), 1))>;
def : Pat<(v2i64 (scalar_to_vector ScalarLoads.SELi16i64)),
(v2i64 (XXPERMDIs (VEXTSH2Ds (LXSIHZX xoaddr:$src)), 0))>;
let Predicates = [IsBigEndian, HasP9Vector] in {
// Scalar stores of i8
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 0)), xoaddr:$dst),
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 9)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 1)), xoaddr:$dst),
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 10)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 2)), xoaddr:$dst),
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 11)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 3)), xoaddr:$dst),
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 12)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 4)), xoaddr:$dst),
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 13)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 5)), xoaddr:$dst),
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 14)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 6)), xoaddr:$dst),
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 15)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 7)), xoaddr:$dst),
(STXSIBXv (COPY_TO_REGCLASS $S, VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 8)), xoaddr:$dst),
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 1)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 9)), xoaddr:$dst),
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 2)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 10)), xoaddr:$dst),
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 3)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 11)), xoaddr:$dst),
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 4)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 12)), xoaddr:$dst),
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 5)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 13)), xoaddr:$dst),
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 6)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 14)), xoaddr:$dst),
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 7)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 15)), xoaddr:$dst),
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 8)), VSRC), xoaddr:$dst)>;
// Scalar stores of i16
def : Pat<(truncstorei16 (i32 (vector_extract v8i16:$S, 0)), xoaddr:$dst),
(STXSIHXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 10)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei16 (i32 (vector_extract v8i16:$S, 1)), xoaddr:$dst),
(STXSIHXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 12)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei16 (i32 (vector_extract v8i16:$S, 2)), xoaddr:$dst),
(STXSIHXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 14)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei16 (i32 (vector_extract v8i16:$S, 3)), xoaddr:$dst),
(STXSIHXv (COPY_TO_REGCLASS $S, VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei16 (i32 (vector_extract v8i16:$S, 4)), xoaddr:$dst),
(STXSIHXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 2)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei16 (i32 (vector_extract v8i16:$S, 5)), xoaddr:$dst),
(STXSIHXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 4)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei16 (i32 (vector_extract v8i16:$S, 6)), xoaddr:$dst),
(STXSIHXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 6)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei16 (i32 (vector_extract v8i16:$S, 7)), xoaddr:$dst),
(STXSIHXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 8)), VSRC), xoaddr:$dst)>;
} // IsBigEndian, HasP9Vector
let Predicates = [IsLittleEndian, HasP9Vector] in {
// Scalar stores of i8
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 0)), xoaddr:$dst),
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 8)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 1)), xoaddr:$dst),
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 7)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 2)), xoaddr:$dst),
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 6)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 3)), xoaddr:$dst),
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 5)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 4)), xoaddr:$dst),
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 4)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 5)), xoaddr:$dst),
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 3)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 6)), xoaddr:$dst),
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 2)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 7)), xoaddr:$dst),
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 1)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 8)), xoaddr:$dst),
(STXSIBXv (COPY_TO_REGCLASS $S, VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 9)), xoaddr:$dst),
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 15)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 10)), xoaddr:$dst),
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 14)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 11)), xoaddr:$dst),
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 13)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 12)), xoaddr:$dst),
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 12)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 13)), xoaddr:$dst),
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 11)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 14)), xoaddr:$dst),
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 10)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 15)), xoaddr:$dst),
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 9)), VSRC), xoaddr:$dst)>;
// Scalar stores of i16
def : Pat<(truncstorei16 (i32 (vector_extract v8i16:$S, 0)), xoaddr:$dst),
(STXSIHXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 8)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei16 (i32 (vector_extract v8i16:$S, 1)), xoaddr:$dst),
(STXSIHXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 6)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei16 (i32 (vector_extract v8i16:$S, 2)), xoaddr:$dst),
(STXSIHXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 4)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei16 (i32 (vector_extract v8i16:$S, 3)), xoaddr:$dst),
(STXSIHXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 2)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei16 (i32 (vector_extract v8i16:$S, 4)), xoaddr:$dst),
(STXSIHXv (COPY_TO_REGCLASS $S, VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei16 (i32 (vector_extract v8i16:$S, 5)), xoaddr:$dst),
(STXSIHXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 14)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei16 (i32 (vector_extract v8i16:$S, 6)), xoaddr:$dst),
(STXSIHXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 12)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei16 (i32 (vector_extract v8i16:$S, 7)), xoaddr:$dst),
(STXSIHXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 10)), VSRC), xoaddr:$dst)>;
} // IsLittleEndian, HasP9Vector
// Vector sign extensions
def : Pat<(f64 (PPCVexts f64:$A, 1)),
(f64 (COPY_TO_REGCLASS (VEXTSB2Ds $A), VSFRC))>;
def : Pat<(f64 (PPCVexts f64:$A, 2)),
(f64 (COPY_TO_REGCLASS (VEXTSH2Ds $A), VSFRC))>;
def DFLOADf32 : PPCPostRAExpPseudo<(outs vssrc:$XT), (ins memrix:$src),
"#DFLOADf32",
[(set f32:$XT, (load iaddrX4:$src))]>;
def DFLOADf64 : PPCPostRAExpPseudo<(outs vsfrc:$XT), (ins memrix:$src),
"#DFLOADf64",
[(set f64:$XT, (load iaddrX4:$src))]>;
def DFSTOREf32 : PPCPostRAExpPseudo<(outs), (ins vssrc:$XT, memrix:$dst),
"#DFSTOREf32",
[(store f32:$XT, iaddrX4:$dst)]>;
def DFSTOREf64 : PPCPostRAExpPseudo<(outs), (ins vsfrc:$XT, memrix:$dst),
"#DFSTOREf64",
[(store f64:$XT, iaddrX4:$dst)]>;
def : Pat<(f64 (extloadf32 iaddrX4:$src)),
(COPY_TO_REGCLASS (DFLOADf32 iaddrX4:$src), VSFRC)>;
def : Pat<(f32 (fpround (f64 (extloadf32 iaddrX4:$src)))),
(f32 (DFLOADf32 iaddrX4:$src))>;
def : Pat<(v4f32 (PPCldvsxlh xaddr:$src)),
(COPY_TO_REGCLASS (XFLOADf64 xaddr:$src), VSRC)>;
def : Pat<(v4f32 (PPCldvsxlh iaddrX4:$src)),
(COPY_TO_REGCLASS (DFLOADf64 iaddrX4:$src), VSRC)>;
let AddedComplexity = 400 in {
// The following pseudoinstructions are used to ensure the utilization
// of all 64 VSX registers.
let Predicates = [IsLittleEndian, HasP9Vector] in {
def : Pat<(v2i64 (scalar_to_vector (i64 (load iaddrX4:$src)))),
(v2i64 (XXPERMDIs
(COPY_TO_REGCLASS (DFLOADf64 iaddrX4:$src), VSRC), 2))>;
def : Pat<(v2i64 (scalar_to_vector (i64 (load xaddrX4:$src)))),
(v2i64 (XXPERMDIs
(COPY_TO_REGCLASS (XFLOADf64 xaddrX4:$src), VSRC), 2))>;
def : Pat<(v2f64 (scalar_to_vector (f64 (load iaddrX4:$src)))),
(v2f64 (XXPERMDIs
(COPY_TO_REGCLASS (DFLOADf64 iaddrX4:$src), VSRC), 2))>;
def : Pat<(v2f64 (scalar_to_vector (f64 (load xaddrX4:$src)))),
(v2f64 (XXPERMDIs
(COPY_TO_REGCLASS (XFLOADf64 xaddrX4:$src), VSRC), 2))>;
def : Pat<(store (i64 (extractelt v2i64:$A, 0)), xaddrX4:$src),
(XFSTOREf64 (EXTRACT_SUBREG (XXPERMDI $A, $A, 2),
sub_64), xaddrX4:$src)>;
def : Pat<(store (f64 (extractelt v2f64:$A, 0)), xaddrX4:$src),
(XFSTOREf64 (EXTRACT_SUBREG (XXPERMDI $A, $A, 2),
sub_64), xaddrX4:$src)>;
def : Pat<(store (i64 (extractelt v2i64:$A, 1)), xaddrX4:$src),
(XFSTOREf64 (EXTRACT_SUBREG $A, sub_64), xaddrX4:$src)>;
def : Pat<(store (f64 (extractelt v2f64:$A, 1)), xaddrX4:$src),
(XFSTOREf64 (EXTRACT_SUBREG $A, sub_64), xaddrX4:$src)>;
def : Pat<(store (i64 (extractelt v2i64:$A, 0)), iaddrX4:$src),
(DFSTOREf64 (EXTRACT_SUBREG (XXPERMDI $A, $A, 2),
sub_64), iaddrX4:$src)>;
def : Pat<(store (f64 (extractelt v2f64:$A, 0)), iaddrX4:$src),
(DFSTOREf64 (EXTRACT_SUBREG (XXPERMDI $A, $A, 2), sub_64),
iaddrX4:$src)>;
def : Pat<(store (i64 (extractelt v2i64:$A, 1)), iaddrX4:$src),
(DFSTOREf64 (EXTRACT_SUBREG $A, sub_64), iaddrX4:$src)>;
def : Pat<(store (f64 (extractelt v2f64:$A, 1)), iaddrX4:$src),
(DFSTOREf64 (EXTRACT_SUBREG $A, sub_64), iaddrX4:$src)>;
} // IsLittleEndian, HasP9Vector
let Predicates = [IsBigEndian, HasP9Vector] in {
def : Pat<(v2i64 (scalar_to_vector (i64 (load iaddrX4:$src)))),
(v2i64 (COPY_TO_REGCLASS (DFLOADf64 iaddrX4:$src), VSRC))>;
def : Pat<(v2i64 (scalar_to_vector (i64 (load xaddrX4:$src)))),
(v2i64 (COPY_TO_REGCLASS (XFLOADf64 xaddrX4:$src), VSRC))>;
def : Pat<(v2f64 (scalar_to_vector (f64 (load iaddrX4:$src)))),
(v2f64 (COPY_TO_REGCLASS (DFLOADf64 iaddrX4:$src), VSRC))>;
def : Pat<(v2f64 (scalar_to_vector (f64 (load xaddrX4:$src)))),
(v2f64 (COPY_TO_REGCLASS (XFLOADf64 xaddrX4:$src), VSRC))>;
def : Pat<(store (i64 (extractelt v2i64:$A, 1)), xaddrX4:$src),
(XFSTOREf64 (EXTRACT_SUBREG (XXPERMDI $A, $A, 2),
sub_64), xaddrX4:$src)>;
def : Pat<(store (f64 (extractelt v2f64:$A, 1)), xaddrX4:$src),
(XFSTOREf64 (EXTRACT_SUBREG (XXPERMDI $A, $A, 2),
sub_64), xaddrX4:$src)>;
def : Pat<(store (i64 (extractelt v2i64:$A, 0)), xaddrX4:$src),
(XFSTOREf64 (EXTRACT_SUBREG $A, sub_64), xaddrX4:$src)>;
def : Pat<(store (f64 (extractelt v2f64:$A, 0)), xaddrX4:$src),
(XFSTOREf64 (EXTRACT_SUBREG $A, sub_64), xaddrX4:$src)>;
def : Pat<(store (i64 (extractelt v2i64:$A, 1)), iaddrX4:$src),
(DFSTOREf64 (EXTRACT_SUBREG (XXPERMDI $A, $A, 2),
sub_64), iaddrX4:$src)>;
def : Pat<(store (f64 (extractelt v2f64:$A, 1)), iaddrX4:$src),
(DFSTOREf64 (EXTRACT_SUBREG (XXPERMDI $A, $A, 2),
sub_64), iaddrX4:$src)>;
def : Pat<(store (i64 (extractelt v2i64:$A, 0)), iaddrX4:$src),
(DFSTOREf64 (EXTRACT_SUBREG $A, sub_64), iaddrX4:$src)>;
def : Pat<(store (f64 (extractelt v2f64:$A, 0)), iaddrX4:$src),
(DFSTOREf64 (EXTRACT_SUBREG $A, sub_64), iaddrX4:$src)>;
} // IsBigEndian, HasP9Vector
}
let Predicates = [IsBigEndian, HasP9Vector] in {
// (Un)Signed DWord vector extract -> QP
def : Pat<(f128 (sint_to_fp (i64 (extractelt v2i64:$src, 0)))),
(f128 (XSCVSDQP (COPY_TO_REGCLASS $src, VFRC)))>;
def : Pat<(f128 (sint_to_fp (i64 (extractelt v2i64:$src, 1)))),
(f128 (XSCVSDQP
(EXTRACT_SUBREG (XXPERMDI $src, $src, 3), sub_64)))>;
def : Pat<(f128 (uint_to_fp (i64 (extractelt v2i64:$src, 0)))),
(f128 (XSCVUDQP (COPY_TO_REGCLASS $src, VFRC)))>;
def : Pat<(f128 (uint_to_fp (i64 (extractelt v2i64:$src, 1)))),
(f128 (XSCVUDQP
(EXTRACT_SUBREG (XXPERMDI $src, $src, 3), sub_64)))>;
// (Un)Signed Word vector extract -> QP
def : Pat<(f128 (sint_to_fp (i32 (extractelt v4i32:$src, 1)))),
(f128 (XSCVSDQP (EXTRACT_SUBREG (VEXTSW2D $src), sub_64)))>;
foreach Idx = [0,2,3] in {
def : Pat<(f128 (sint_to_fp (i32 (extractelt v4i32:$src, Idx)))),
(f128 (XSCVSDQP (EXTRACT_SUBREG
(VEXTSW2D (VSPLTW Idx, $src)), sub_64)))>;
}
foreach Idx = 0-3 in {
def : Pat<(f128 (uint_to_fp (i32 (extractelt v4i32:$src, Idx)))),
(f128 (XSCVUDQP (XXEXTRACTUW $src, !shl(Idx, 2))))>;
}
// (Un)Signed HWord vector extract -> QP
foreach Idx = 0-7 in {
def : Pat<(f128 (sint_to_fp
(i32 (sext_inreg
(vector_extract v8i16:$src, Idx), i16)))),
(f128 (XSCVSDQP (EXTRACT_SUBREG
(VEXTSH2D (VEXTRACTUH !add(Idx, Idx), $src)),
sub_64)))>;
// The SDAG adds the `and` since an `i16` is being extracted as an `i32`.
def : Pat<(f128 (uint_to_fp
(and (i32 (vector_extract v8i16:$src, Idx)), 65535))),
(f128 (XSCVUDQP (EXTRACT_SUBREG
(VEXTRACTUH !add(Idx, Idx), $src), sub_64)))>;
}
// (Un)Signed Byte vector extract -> QP
foreach Idx = 0-15 in {
def : Pat<(f128 (sint_to_fp
(i32 (sext_inreg (vector_extract v16i8:$src, Idx),
i8)))),
(f128 (XSCVSDQP (EXTRACT_SUBREG
(VEXTSB2D (VEXTRACTUB Idx, $src)), sub_64)))>;
def : Pat<(f128 (uint_to_fp
(and (i32 (vector_extract v16i8:$src, Idx)), 255))),
(f128 (XSCVUDQP
(EXTRACT_SUBREG (VEXTRACTUB Idx, $src), sub_64)))>;
}
// Unsiged int in vsx register -> QP
def : Pat<(f128 (uint_to_fp (i32 (PPCmfvsr f64:$src)))),
(f128 (XSCVUDQP
(XXEXTRACTUW (SUBREG_TO_REG (i64 1), $src, sub_64), 4)))>;
} // IsBigEndian, HasP9Vector
let Predicates = [IsLittleEndian, HasP9Vector] in {
// (Un)Signed DWord vector extract -> QP
def : Pat<(f128 (sint_to_fp (i64 (extractelt v2i64:$src, 0)))),
(f128 (XSCVSDQP
(EXTRACT_SUBREG (XXPERMDI $src, $src, 3), sub_64)))>;
def : Pat<(f128 (sint_to_fp (i64 (extractelt v2i64:$src, 1)))),
(f128 (XSCVSDQP (COPY_TO_REGCLASS $src, VFRC)))>;
def : Pat<(f128 (uint_to_fp (i64 (extractelt v2i64:$src, 0)))),
(f128 (XSCVUDQP
(EXTRACT_SUBREG (XXPERMDI $src, $src, 3), sub_64)))>;
def : Pat<(f128 (uint_to_fp (i64 (extractelt v2i64:$src, 1)))),
(f128 (XSCVUDQP (COPY_TO_REGCLASS $src, VFRC)))>;
// (Un)Signed Word vector extract -> QP
foreach Idx = [[0,3],[1,2],[3,0]] in {
def : Pat<(f128 (sint_to_fp (i32 (extractelt v4i32:$src, !head(Idx))))),
(f128 (XSCVSDQP (EXTRACT_SUBREG
(VEXTSW2D (VSPLTW !head(!tail(Idx)), $src)),
sub_64)))>;
}
def : Pat<(f128 (sint_to_fp (i32 (extractelt v4i32:$src, 2)))),
(f128 (XSCVSDQP (EXTRACT_SUBREG (VEXTSW2D $src), sub_64)))>;
foreach Idx = [[0,12],[1,8],[2,4],[3,0]] in {
def : Pat<(f128 (uint_to_fp (i32 (extractelt v4i32:$src, !head(Idx))))),
(f128 (XSCVUDQP (XXEXTRACTUW $src, !head(!tail(Idx)))))>;
}
// (Un)Signed HWord vector extract -> QP
// The Nested foreach lists identifies the vector element and corresponding
// register byte location.
foreach Idx = [[0,14],[1,12],[2,10],[3,8],[4,6],[5,4],[6,2],[7,0]] in {
def : Pat<(f128 (sint_to_fp
(i32 (sext_inreg
(vector_extract v8i16:$src, !head(Idx)), i16)))),
(f128 (XSCVSDQP
(EXTRACT_SUBREG (VEXTSH2D
(VEXTRACTUH !head(!tail(Idx)), $src)),
sub_64)))>;
def : Pat<(f128 (uint_to_fp
(and (i32 (vector_extract v8i16:$src, !head(Idx))),
65535))),
(f128 (XSCVUDQP (EXTRACT_SUBREG
(VEXTRACTUH !head(!tail(Idx)), $src), sub_64)))>;
}
// (Un)Signed Byte vector extract -> QP
foreach Idx = [[0,15],[1,14],[2,13],[3,12],[4,11],[5,10],[6,9],[7,8],[8,7],
[9,6],[10,5],[11,4],[12,3],[13,2],[14,1],[15,0]] in {
def : Pat<(f128 (sint_to_fp
(i32 (sext_inreg
(vector_extract v16i8:$src, !head(Idx)), i8)))),
(f128 (XSCVSDQP
(EXTRACT_SUBREG
(VEXTSB2D (VEXTRACTUB !head(!tail(Idx)), $src)),
sub_64)))>;
def : Pat<(f128 (uint_to_fp
(and (i32 (vector_extract v16i8:$src, !head(Idx))),
255))),
(f128 (XSCVUDQP
(EXTRACT_SUBREG
(VEXTRACTUB !head(!tail(Idx)), $src), sub_64)))>;
}
// Unsiged int in vsx register -> QP
def : Pat<(f128 (uint_to_fp (i32 (PPCmfvsr f64:$src)))),
(f128 (XSCVUDQP
(XXEXTRACTUW (SUBREG_TO_REG (i64 1), $src, sub_64), 8)))>;
} // IsLittleEndian, HasP9Vector
// Convert (Un)Signed DWord in memory -> QP
def : Pat<(f128 (sint_to_fp (i64 (load xaddrX4:$src)))),
(f128 (XSCVSDQP (LXSDX xaddrX4:$src)))>;
def : Pat<(f128 (sint_to_fp (i64 (load iaddrX4:$src)))),
(f128 (XSCVSDQP (LXSD iaddrX4:$src)))>;
def : Pat<(f128 (uint_to_fp (i64 (load xaddrX4:$src)))),
(f128 (XSCVUDQP (LXSDX xaddrX4:$src)))>;
def : Pat<(f128 (uint_to_fp (i64 (load iaddrX4:$src)))),
(f128 (XSCVUDQP (LXSD iaddrX4:$src)))>;
// Convert Unsigned HWord in memory -> QP
def : Pat<(f128 (uint_to_fp ScalarLoads.ZELi16)),
(f128 (XSCVUDQP (LXSIHZX xaddr:$src)))>;
// Convert Unsigned Byte in memory -> QP
def : Pat<(f128 (uint_to_fp ScalarLoads.ZELi8)),
(f128 (XSCVUDQP (LXSIBZX xoaddr:$src)))>;
// Truncate & Convert QP -> (Un)Signed (D)Word.
def : Pat<(i64 (fp_to_sint f128:$src)), (i64 (MFVRD (XSCVQPSDZ $src)))>;
def : Pat<(i64 (fp_to_uint f128:$src)), (i64 (MFVRD (XSCVQPUDZ $src)))>;
def : Pat<(i32 (fp_to_sint f128:$src)),
(i32 (MFVSRWZ (COPY_TO_REGCLASS (XSCVQPSWZ $src), VFRC)))>;
def : Pat<(i32 (fp_to_uint f128:$src)),
(i32 (MFVSRWZ (COPY_TO_REGCLASS (XSCVQPUWZ $src), VFRC)))>;
// Instructions for store(fptosi).
// The 8-byte version is repeated here due to availability of D-Form STXSD.
def : Pat<(PPCstore_scal_int_from_vsr
(f64 (PPCcv_fp_to_sint_in_vsr f128:$src)), xaddrX4:$dst, 8),
(STXSDX (COPY_TO_REGCLASS (XSCVQPSDZ f128:$src), VFRC),
xaddrX4:$dst)>;
def : Pat<(PPCstore_scal_int_from_vsr
(f64 (PPCcv_fp_to_sint_in_vsr f128:$src)), iaddrX4:$dst, 8),
(STXSD (COPY_TO_REGCLASS (XSCVQPSDZ f128:$src), VFRC),
iaddrX4:$dst)>;
def : Pat<(PPCstore_scal_int_from_vsr
(f64 (PPCcv_fp_to_sint_in_vsr f128:$src)), xoaddr:$dst, 4),
(STXSIWX (COPY_TO_REGCLASS (XSCVQPSWZ $src), VFRC), xoaddr:$dst)>;
def : Pat<(PPCstore_scal_int_from_vsr
(f64 (PPCcv_fp_to_sint_in_vsr f128:$src)), xoaddr:$dst, 2),
(STXSIHX (COPY_TO_REGCLASS (XSCVQPSWZ $src), VFRC), xoaddr:$dst)>;
def : Pat<(PPCstore_scal_int_from_vsr
(f64 (PPCcv_fp_to_sint_in_vsr f128:$src)), xoaddr:$dst, 1),
(STXSIBX (COPY_TO_REGCLASS (XSCVQPSWZ $src), VFRC), xoaddr:$dst)>;
def : Pat<(PPCstore_scal_int_from_vsr
(f64 (PPCcv_fp_to_sint_in_vsr f64:$src)), xaddrX4:$dst, 8),
(STXSDX (XSCVDPSXDS f64:$src), xaddrX4:$dst)>;
def : Pat<(PPCstore_scal_int_from_vsr
(f64 (PPCcv_fp_to_sint_in_vsr f64:$src)), iaddrX4:$dst, 8),
(STXSD (XSCVDPSXDS f64:$src), iaddrX4:$dst)>;
def : Pat<(PPCstore_scal_int_from_vsr
(f64 (PPCcv_fp_to_sint_in_vsr f64:$src)), xoaddr:$dst, 2),
(STXSIHX (XSCVDPSXWS f64:$src), xoaddr:$dst)>;
def : Pat<(PPCstore_scal_int_from_vsr
(f64 (PPCcv_fp_to_sint_in_vsr f64:$src)), xoaddr:$dst, 1),
(STXSIBX (XSCVDPSXWS f64:$src), xoaddr:$dst)>;
// Instructions for store(fptoui).
def : Pat<(PPCstore_scal_int_from_vsr
(f64 (PPCcv_fp_to_uint_in_vsr f128:$src)), xaddrX4:$dst, 8),
(STXSDX (COPY_TO_REGCLASS (XSCVQPUDZ f128:$src), VFRC),
xaddrX4:$dst)>;
def : Pat<(PPCstore_scal_int_from_vsr
(f64 (PPCcv_fp_to_uint_in_vsr f128:$src)), iaddrX4:$dst, 8),
(STXSD (COPY_TO_REGCLASS (XSCVQPUDZ f128:$src), VFRC),
iaddrX4:$dst)>;
def : Pat<(PPCstore_scal_int_from_vsr
(f64 (PPCcv_fp_to_uint_in_vsr f128:$src)), xoaddr:$dst, 4),
(STXSIWX (COPY_TO_REGCLASS (XSCVQPUWZ $src), VFRC), xoaddr:$dst)>;
def : Pat<(PPCstore_scal_int_from_vsr
(f64 (PPCcv_fp_to_uint_in_vsr f128:$src)), xoaddr:$dst, 2),
(STXSIHX (COPY_TO_REGCLASS (XSCVQPUWZ $src), VFRC), xoaddr:$dst)>;
def : Pat<(PPCstore_scal_int_from_vsr
(f64 (PPCcv_fp_to_uint_in_vsr f128:$src)), xoaddr:$dst, 1),
(STXSIBX (COPY_TO_REGCLASS (XSCVQPUWZ $src), VFRC), xoaddr:$dst)>;
def : Pat<(PPCstore_scal_int_from_vsr
(f64 (PPCcv_fp_to_uint_in_vsr f64:$src)), xaddrX4:$dst, 8),
(STXSDX (XSCVDPUXDS f64:$src), xaddrX4:$dst)>;
def : Pat<(PPCstore_scal_int_from_vsr
(f64 (PPCcv_fp_to_uint_in_vsr f64:$src)), iaddrX4:$dst, 8),
(STXSD (XSCVDPUXDS f64:$src), iaddrX4:$dst)>;
def : Pat<(PPCstore_scal_int_from_vsr
(f64 (PPCcv_fp_to_uint_in_vsr f64:$src)), xoaddr:$dst, 2),
(STXSIHX (XSCVDPUXWS f64:$src), xoaddr:$dst)>;
def : Pat<(PPCstore_scal_int_from_vsr
(f64 (PPCcv_fp_to_uint_in_vsr f64:$src)), xoaddr:$dst, 1),
(STXSIBX (XSCVDPUXWS f64:$src), xoaddr:$dst)>;
// Round & Convert QP -> DP/SP
def : Pat<(f64 (fpround f128:$src)), (f64 (XSCVQPDP $src))>;
def : Pat<(f32 (fpround f128:$src)), (f32 (XSRSP (XSCVQPDPO $src)))>;
// Convert SP -> QP
def : Pat<(f128 (fpextend f32:$src)),
(f128 (XSCVDPQP (COPY_TO_REGCLASS $src, VFRC)))>;
def : Pat<(f32 (PPCxsmaxc f32:$XA, f32:$XB)),
(f32 (COPY_TO_REGCLASS (XSMAXCDP (COPY_TO_REGCLASS $XA, VSSRC),
(COPY_TO_REGCLASS $XB, VSSRC)),
VSSRC))>;
def : Pat<(f32 (PPCxsminc f32:$XA, f32:$XB)),
(f32 (COPY_TO_REGCLASS (XSMINCDP (COPY_TO_REGCLASS $XA, VSSRC),
(COPY_TO_REGCLASS $XB, VSSRC)),
VSSRC))>;
} // end HasP9Vector, AddedComplexity
let AddedComplexity = 400 in {
let Predicates = [IsISA3_0, HasP9Vector, HasDirectMove, IsBigEndian] in {
def : Pat<(f128 (PPCbuild_fp128 i64:$rB, i64:$rA)),
(f128 (COPY_TO_REGCLASS (MTVSRDD $rB, $rA), VRRC))>;
}
let Predicates = [IsISA3_0, HasP9Vector, HasDirectMove, IsLittleEndian] in {
def : Pat<(f128 (PPCbuild_fp128 i64:$rA, i64:$rB)),
(f128 (COPY_TO_REGCLASS (MTVSRDD $rB, $rA), VRRC))>;
}
}
let Predicates = [HasP9Vector] in {
let mayStore = 1 in {
def SPILLTOVSR_STX : PseudoXFormMemOp<(outs),
(ins spilltovsrrc:$XT, memrr:$dst),
"#SPILLTOVSR_STX", []>;
def SPILLTOVSR_ST : PPCPostRAExpPseudo<(outs), (ins spilltovsrrc:$XT, memrix:$dst),
"#SPILLTOVSR_ST", []>;
}
let mayLoad = 1 in {
def SPILLTOVSR_LDX : PseudoXFormMemOp<(outs spilltovsrrc:$XT),
(ins memrr:$src),
"#SPILLTOVSR_LDX", []>;
def SPILLTOVSR_LD : PPCPostRAExpPseudo<(outs spilltovsrrc:$XT), (ins memrix:$src),
"#SPILLTOVSR_LD", []>;
}
}
// Integer extend helper dags 32 -> 64
def AnyExts {
dag A = (INSERT_SUBREG (i64 (IMPLICIT_DEF)), $A, sub_32);
dag B = (INSERT_SUBREG (i64 (IMPLICIT_DEF)), $B, sub_32);
dag C = (INSERT_SUBREG (i64 (IMPLICIT_DEF)), $C, sub_32);
dag D = (INSERT_SUBREG (i64 (IMPLICIT_DEF)), $D, sub_32);
}
def DblToFlt {
dag A0 = (f32 (fpround (f64 (extractelt v2f64:$A, 0))));
dag A1 = (f32 (fpround (f64 (extractelt v2f64:$A, 1))));
dag B0 = (f32 (fpround (f64 (extractelt v2f64:$B, 0))));
dag B1 = (f32 (fpround (f64 (extractelt v2f64:$B, 1))));
}
def ExtDbl {
dag A0S = (i32 (PPCmfvsr (f64 (PPCfctiwz (f64 (extractelt v2f64:$A, 0))))));
dag A1S = (i32 (PPCmfvsr (f64 (PPCfctiwz (f64 (extractelt v2f64:$A, 1))))));
dag B0S = (i32 (PPCmfvsr (f64 (PPCfctiwz (f64 (extractelt v2f64:$B, 0))))));
dag B1S = (i32 (PPCmfvsr (f64 (PPCfctiwz (f64 (extractelt v2f64:$B, 1))))));
dag A0U = (i32 (PPCmfvsr (f64 (PPCfctiwuz (f64 (extractelt v2f64:$A, 0))))));
dag A1U = (i32 (PPCmfvsr (f64 (PPCfctiwuz (f64 (extractelt v2f64:$A, 1))))));
dag B0U = (i32 (PPCmfvsr (f64 (PPCfctiwuz (f64 (extractelt v2f64:$B, 0))))));
dag B1U = (i32 (PPCmfvsr (f64 (PPCfctiwuz (f64 (extractelt v2f64:$B, 1))))));
}
def ByteToWord {
dag LE_A0 = (i32 (sext_inreg (i32 (vector_extract v16i8:$A, 0)), i8));
dag LE_A1 = (i32 (sext_inreg (i32 (vector_extract v16i8:$A, 4)), i8));
dag LE_A2 = (i32 (sext_inreg (i32 (vector_extract v16i8:$A, 8)), i8));
dag LE_A3 = (i32 (sext_inreg (i32 (vector_extract v16i8:$A, 12)), i8));
dag BE_A0 = (i32 (sext_inreg (i32 (vector_extract v16i8:$A, 3)), i8));
dag BE_A1 = (i32 (sext_inreg (i32 (vector_extract v16i8:$A, 7)), i8));
dag BE_A2 = (i32 (sext_inreg (i32 (vector_extract v16i8:$A, 11)), i8));
dag BE_A3 = (i32 (sext_inreg (i32 (vector_extract v16i8:$A, 15)), i8));
}
def ByteToDWord {
dag LE_A0 = (i64 (sext_inreg
(i64 (anyext (i32 (vector_extract v16i8:$A, 0)))), i8));
dag LE_A1 = (i64 (sext_inreg
(i64 (anyext (i32 (vector_extract v16i8:$A, 8)))), i8));
dag BE_A0 = (i64 (sext_inreg
(i64 (anyext (i32 (vector_extract v16i8:$A, 7)))), i8));
dag BE_A1 = (i64 (sext_inreg
(i64 (anyext (i32 (vector_extract v16i8:$A, 15)))), i8));
}
def HWordToWord {
dag LE_A0 = (i32 (sext_inreg (i32 (vector_extract v8i16:$A, 0)), i16));
dag LE_A1 = (i32 (sext_inreg (i32 (vector_extract v8i16:$A, 2)), i16));
dag LE_A2 = (i32 (sext_inreg (i32 (vector_extract v8i16:$A, 4)), i16));
dag LE_A3 = (i32 (sext_inreg (i32 (vector_extract v8i16:$A, 6)), i16));
dag BE_A0 = (i32 (sext_inreg (i32 (vector_extract v8i16:$A, 1)), i16));
dag BE_A1 = (i32 (sext_inreg (i32 (vector_extract v8i16:$A, 3)), i16));
dag BE_A2 = (i32 (sext_inreg (i32 (vector_extract v8i16:$A, 5)), i16));
dag BE_A3 = (i32 (sext_inreg (i32 (vector_extract v8i16:$A, 7)), i16));
}
def HWordToDWord {
dag LE_A0 = (i64 (sext_inreg
(i64 (anyext (i32 (vector_extract v8i16:$A, 0)))), i16));
dag LE_A1 = (i64 (sext_inreg
(i64 (anyext (i32 (vector_extract v8i16:$A, 4)))), i16));
dag BE_A0 = (i64 (sext_inreg
(i64 (anyext (i32 (vector_extract v8i16:$A, 3)))), i16));
dag BE_A1 = (i64 (sext_inreg
(i64 (anyext (i32 (vector_extract v8i16:$A, 7)))), i16));
}
def WordToDWord {
dag LE_A0 = (i64 (sext (i32 (vector_extract v4i32:$A, 0))));
dag LE_A1 = (i64 (sext (i32 (vector_extract v4i32:$A, 2))));
dag BE_A0 = (i64 (sext (i32 (vector_extract v4i32:$A, 1))));
dag BE_A1 = (i64 (sext (i32 (vector_extract v4i32:$A, 3))));
}
def FltToIntLoad {
dag A = (i32 (PPCmfvsr (PPCfctiwz (f64 (extloadf32 xoaddr:$A)))));
}
def FltToUIntLoad {
dag A = (i32 (PPCmfvsr (PPCfctiwuz (f64 (extloadf32 xoaddr:$A)))));
}
def FltToLongLoad {
dag A = (i64 (PPCmfvsr (PPCfctidz (f64 (extloadf32 xoaddr:$A)))));
}
def FltToLongLoadP9 {
dag A = (i64 (PPCmfvsr (PPCfctidz (f64 (extloadf32 iaddrX4:$A)))));
}
def FltToULongLoad {
dag A = (i64 (PPCmfvsr (PPCfctiduz (f64 (extloadf32 xoaddr:$A)))));
}
def FltToULongLoadP9 {
dag A = (i64 (PPCmfvsr (PPCfctiduz (f64 (extloadf32 iaddrX4:$A)))));
}
def FltToLong {
dag A = (i64 (PPCmfvsr (f64 (PPCfctidz (fpextend f32:$A)))));
}
def FltToULong {
dag A = (i64 (PPCmfvsr (f64 (PPCfctiduz (fpextend f32:$A)))));
}
def DblToInt {
dag A = (i32 (PPCmfvsr (f64 (PPCfctiwz f64:$A))));
dag B = (i32 (PPCmfvsr (f64 (PPCfctiwz f64:$B))));
dag C = (i32 (PPCmfvsr (f64 (PPCfctiwz f64:$C))));
dag D = (i32 (PPCmfvsr (f64 (PPCfctiwz f64:$D))));
}
def DblToUInt {
dag A = (i32 (PPCmfvsr (f64 (PPCfctiwuz f64:$A))));
dag B = (i32 (PPCmfvsr (f64 (PPCfctiwuz f64:$B))));
dag C = (i32 (PPCmfvsr (f64 (PPCfctiwuz f64:$C))));
dag D = (i32 (PPCmfvsr (f64 (PPCfctiwuz f64:$D))));
}
def DblToLong {
dag A = (i64 (PPCmfvsr (f64 (PPCfctidz f64:$A))));
}
def DblToULong {
dag A = (i64 (PPCmfvsr (f64 (PPCfctiduz f64:$A))));
}
def DblToIntLoad {
dag A = (i32 (PPCmfvsr (PPCfctiwz (f64 (load xoaddr:$A)))));
}
def DblToIntLoadP9 {
dag A = (i32 (PPCmfvsr (PPCfctiwz (f64 (load iaddrX4:$A)))));
}
def DblToUIntLoad {
dag A = (i32 (PPCmfvsr (PPCfctiwuz (f64 (load xoaddr:$A)))));
}
def DblToUIntLoadP9 {
dag A = (i32 (PPCmfvsr (PPCfctiwuz (f64 (load iaddrX4:$A)))));
}
def DblToLongLoad {
dag A = (i64 (PPCmfvsr (PPCfctidz (f64 (load xoaddr:$A)))));
}
def DblToULongLoad {
dag A = (i64 (PPCmfvsr (PPCfctiduz (f64 (load xoaddr:$A)))));
}
// FP merge dags (for f32 -> v4f32)
def MrgFP {
dag AC = (XVCVDPSP (XXPERMDI (COPY_TO_REGCLASS $A, VSRC),
(COPY_TO_REGCLASS $C, VSRC), 0));
dag BD = (XVCVDPSP (XXPERMDI (COPY_TO_REGCLASS $B, VSRC),
(COPY_TO_REGCLASS $D, VSRC), 0));
dag ABhToFlt = (XVCVDPSP (XXPERMDI $A, $B, 0));
dag ABlToFlt = (XVCVDPSP (XXPERMDI $A, $B, 3));
dag BAhToFlt = (XVCVDPSP (XXPERMDI $B, $A, 0));
dag BAlToFlt = (XVCVDPSP (XXPERMDI $B, $A, 3));
}
// Word-element merge dags - conversions from f64 to i32 merged into vectors.
def MrgWords {
// For big endian, we merge low and hi doublewords (A, B).
dag A0B0 = (v2f64 (XXPERMDI v2f64:$A, v2f64:$B, 0));
dag A1B1 = (v2f64 (XXPERMDI v2f64:$A, v2f64:$B, 3));
dag CVA1B1S = (v4i32 (XVCVDPSXWS A1B1));
dag CVA0B0S = (v4i32 (XVCVDPSXWS A0B0));
dag CVA1B1U = (v4i32 (XVCVDPUXWS A1B1));
dag CVA0B0U = (v4i32 (XVCVDPUXWS A0B0));
// For little endian, we merge low and hi doublewords (B, A).
dag B1A1 = (v2f64 (XXPERMDI v2f64:$B, v2f64:$A, 0));
dag B0A0 = (v2f64 (XXPERMDI v2f64:$B, v2f64:$A, 3));
dag CVB1A1S = (v4i32 (XVCVDPSXWS B1A1));
dag CVB0A0S = (v4i32 (XVCVDPSXWS B0A0));
dag CVB1A1U = (v4i32 (XVCVDPUXWS B1A1));
dag CVB0A0U = (v4i32 (XVCVDPUXWS B0A0));
// For big endian, we merge hi doublewords of (A, C) and (B, D), convert
// then merge.
dag AC = (v2f64 (XXPERMDI (COPY_TO_REGCLASS f64:$A, VSRC),
(COPY_TO_REGCLASS f64:$C, VSRC), 0));
dag BD = (v2f64 (XXPERMDI (COPY_TO_REGCLASS f64:$B, VSRC),
(COPY_TO_REGCLASS f64:$D, VSRC), 0));
dag CVACS = (v4i32 (XVCVDPSXWS AC));
dag CVBDS = (v4i32 (XVCVDPSXWS BD));
dag CVACU = (v4i32 (XVCVDPUXWS AC));
dag CVBDU = (v4i32 (XVCVDPUXWS BD));
// For little endian, we merge hi doublewords of (D, B) and (C, A), convert
// then merge.
dag DB = (v2f64 (XXPERMDI (COPY_TO_REGCLASS f64:$D, VSRC),
(COPY_TO_REGCLASS f64:$B, VSRC), 0));
dag CA = (v2f64 (XXPERMDI (COPY_TO_REGCLASS f64:$C, VSRC),
(COPY_TO_REGCLASS f64:$A, VSRC), 0));
dag CVDBS = (v4i32 (XVCVDPSXWS DB));
dag CVCAS = (v4i32 (XVCVDPSXWS CA));
dag CVDBU = (v4i32 (XVCVDPUXWS DB));
dag CVCAU = (v4i32 (XVCVDPUXWS CA));
}
// Patterns for BUILD_VECTOR nodes.
let AddedComplexity = 400 in {
let Predicates = [HasVSX] in {
// Build vectors of floating point converted to i32.
def : Pat<(v4i32 (build_vector DblToInt.A, DblToInt.A,
DblToInt.A, DblToInt.A)),
(v4i32 (XXSPLTW (COPY_TO_REGCLASS (XSCVDPSXWS $A), VSRC), 1))>;
def : Pat<(v4i32 (build_vector DblToUInt.A, DblToUInt.A,
DblToUInt.A, DblToUInt.A)),
(v4i32 (XXSPLTW (COPY_TO_REGCLASS (XSCVDPUXWS $A), VSRC), 1))>;
def : Pat<(v2i64 (build_vector DblToLong.A, DblToLong.A)),
(v2i64 (XXPERMDI (COPY_TO_REGCLASS (XSCVDPSXDS $A), VSRC),
(COPY_TO_REGCLASS (XSCVDPSXDS $A), VSRC), 0))>;
def : Pat<(v2i64 (build_vector DblToULong.A, DblToULong.A)),
(v2i64 (XXPERMDI (COPY_TO_REGCLASS (XSCVDPUXDS $A), VSRC),
(COPY_TO_REGCLASS (XSCVDPUXDS $A), VSRC), 0))>;
def : Pat<(v4i32 (scalar_to_vector FltToIntLoad.A)),
(v4i32 (XXSPLTW (COPY_TO_REGCLASS
(XSCVDPSXWSs (XFLOADf32 xoaddr:$A)), VSRC), 1))>;
def : Pat<(v4i32 (scalar_to_vector FltToUIntLoad.A)),
(v4i32 (XXSPLTW (COPY_TO_REGCLASS
(XSCVDPUXWSs (XFLOADf32 xoaddr:$A)), VSRC), 1))>;
def : Pat<(v4f32 (build_vector f32:$A, f32:$A, f32:$A, f32:$A)),
(v4f32 (XXSPLTW (v4f32 (XSCVDPSPN $A)), 0))>;
def : Pat<(v2f64 (PPCldsplat xoaddr:$A)),
(v2f64 (LXVDSX xoaddr:$A))>;
def : Pat<(v2i64 (PPCldsplat xoaddr:$A)),
(v2i64 (LXVDSX xoaddr:$A))>;
// Build vectors of floating point converted to i64.
def : Pat<(v2i64 (build_vector FltToLong.A, FltToLong.A)),
(v2i64 (XXPERMDIs
(COPY_TO_REGCLASS (XSCVDPSXDSs $A), VSFRC), 0))>;
def : Pat<(v2i64 (build_vector FltToULong.A, FltToULong.A)),
(v2i64 (XXPERMDIs
(COPY_TO_REGCLASS (XSCVDPUXDSs $A), VSFRC), 0))>;
def : Pat<(v2i64 (scalar_to_vector DblToLongLoad.A)),
(v2i64 (XVCVDPSXDS (LXVDSX xoaddr:$A)))>;
def : Pat<(v2i64 (scalar_to_vector DblToULongLoad.A)),
(v2i64 (XVCVDPUXDS (LXVDSX xoaddr:$A)))>;
}
let Predicates = [HasVSX, NoP9Vector] in {
// Load-and-splat with fp-to-int conversion (using X-Form VSX/FP loads).
def : Pat<(v4i32 (scalar_to_vector DblToIntLoad.A)),
(v4i32 (XXSPLTW (COPY_TO_REGCLASS
(XSCVDPSXWS (XFLOADf64 xoaddr:$A)), VSRC), 1))>;
def : Pat<(v4i32 (scalar_to_vector DblToUIntLoad.A)),
(v4i32 (XXSPLTW (COPY_TO_REGCLASS
(XSCVDPUXWS (XFLOADf64 xoaddr:$A)), VSRC), 1))>;
def : Pat<(v2i64 (scalar_to_vector FltToLongLoad.A)),
(v2i64 (XXPERMDIs (XSCVDPSXDS (COPY_TO_REGCLASS
(XFLOADf32 xoaddr:$A), VSFRC)), 0))>;
def : Pat<(v2i64 (scalar_to_vector FltToULongLoad.A)),
(v2i64 (XXPERMDIs (XSCVDPUXDS (COPY_TO_REGCLASS
(XFLOADf32 xoaddr:$A), VSFRC)), 0))>;
}
let Predicates = [IsBigEndian, HasP8Vector] in {
def : Pat<DWToSPExtractConv.BVU,
(v4f32 (VPKUDUM (XXSLDWI (XVCVUXDSP $S1), (XVCVUXDSP $S1), 3),
(XXSLDWI (XVCVUXDSP $S2), (XVCVUXDSP $S2), 3)))>;
def : Pat<DWToSPExtractConv.BVS,
(v4f32 (VPKUDUM (XXSLDWI (XVCVSXDSP $S1), (XVCVSXDSP $S1), 3),
(XXSLDWI (XVCVSXDSP $S2), (XVCVSXDSP $S2), 3)))>;
def : Pat<(store (i32 (extractelt v4i32:$A, 1)), xoaddr:$src),
(STIWX (EXTRACT_SUBREG $A, sub_64), xoaddr:$src)>;
def : Pat<(store (f32 (extractelt v4f32:$A, 1)), xoaddr:$src),
(STIWX (EXTRACT_SUBREG $A, sub_64), xoaddr:$src)>;
// Elements in a register on a BE system are in order <0, 1, 2, 3>.
// The store instructions store the second word from the left.
// So to align element zero, we need to modulo-left-shift by 3 words.
// Similar logic applies for elements 2 and 3.
foreach Idx = [ [0,3], [2,1], [3,2] ] in {
def : Pat<(store (i32 (extractelt v4i32:$A, !head(Idx))), xoaddr:$src),
(STIWX (EXTRACT_SUBREG (XXSLDWI $A, $A, !head(!tail(Idx))),
sub_64), xoaddr:$src)>;
def : Pat<(store (f32 (extractelt v4f32:$A, !head(Idx))), xoaddr:$src),
(STIWX (EXTRACT_SUBREG (XXSLDWI $A, $A, !head(!tail(Idx))),
sub_64), xoaddr:$src)>;
}
}
let Predicates = [HasP8Vector, IsBigEndian, NoP9Vector] in {
def : Pat<(store (i64 (extractelt v2i64:$A, 0)), xoaddr:$src),
(XFSTOREf64 (EXTRACT_SUBREG $A, sub_64), xoaddr:$src)>;
def : Pat<(store (f64 (extractelt v2f64:$A, 0)), xoaddr:$src),
(XFSTOREf64 (EXTRACT_SUBREG $A, sub_64), xoaddr:$src)>;
def : Pat<(store (i64 (extractelt v2i64:$A, 1)), xoaddr:$src),
(XFSTOREf64 (EXTRACT_SUBREG (XXPERMDI $A, $A, 2), sub_64),
xoaddr:$src)>;
def : Pat<(store (f64 (extractelt v2f64:$A, 1)), xoaddr:$src),
(XFSTOREf64 (EXTRACT_SUBREG (XXPERMDI $A, $A, 2), sub_64),
xoaddr:$src)>;
}
// Big endian, available on all targets with VSX
let Predicates = [IsBigEndian, HasVSX] in {
def : Pat<(v2f64 (build_vector f64:$A, f64:$B)),
(v2f64 (XXPERMDI
(COPY_TO_REGCLASS $A, VSRC),
(COPY_TO_REGCLASS $B, VSRC), 0))>;
def : Pat<(v4f32 (build_vector f32:$A, f32:$B, f32:$C, f32:$D)),
(VMRGEW MrgFP.AC, MrgFP.BD)>;
def : Pat<(v4f32 (build_vector DblToFlt.A0, DblToFlt.A1,
DblToFlt.B0, DblToFlt.B1)),
(v4f32 (VMRGEW MrgFP.ABhToFlt, MrgFP.ABlToFlt))>;
// Convert 4 doubles to a vector of ints.
def : Pat<(v4i32 (build_vector DblToInt.A, DblToInt.B,
DblToInt.C, DblToInt.D)),
(v4i32 (VMRGEW MrgWords.CVACS, MrgWords.CVBDS))>;
def : Pat<(v4i32 (build_vector DblToUInt.A, DblToUInt.B,
DblToUInt.C, DblToUInt.D)),
(v4i32 (VMRGEW MrgWords.CVACU, MrgWords.CVBDU))>;
def : Pat<(v4i32 (build_vector ExtDbl.A0S, ExtDbl.A1S,
ExtDbl.B0S, ExtDbl.B1S)),
(v4i32 (VMRGEW MrgWords.CVA0B0S, MrgWords.CVA1B1S))>;
def : Pat<(v4i32 (build_vector ExtDbl.A0U, ExtDbl.A1U,
ExtDbl.B0U, ExtDbl.B1U)),
(v4i32 (VMRGEW MrgWords.CVA0B0U, MrgWords.CVA1B1U))>;
}
let Predicates = [IsLittleEndian, HasP8Vector] in {
def : Pat<DWToSPExtractConv.BVU,
(v4f32 (VPKUDUM (XXSLDWI (XVCVUXDSP $S2), (XVCVUXDSP $S2), 3),
(XXSLDWI (XVCVUXDSP $S1), (XVCVUXDSP $S1), 3)))>;
def : Pat<DWToSPExtractConv.BVS,
(v4f32 (VPKUDUM (XXSLDWI (XVCVSXDSP $S2), (XVCVSXDSP $S2), 3),
(XXSLDWI (XVCVSXDSP $S1), (XVCVSXDSP $S1), 3)))>;
def : Pat<(store (i32 (extractelt v4i32:$A, 2)), xoaddr:$src),
(STIWX (EXTRACT_SUBREG $A, sub_64), xoaddr:$src)>;
def : Pat<(store (f32 (extractelt v4f32:$A, 2)), xoaddr:$src),
(STIWX (EXTRACT_SUBREG $A, sub_64), xoaddr:$src)>;
// Elements in a register on a LE system are in order <3, 2, 1, 0>.
// The store instructions store the second word from the left.
// So to align element 3, we need to modulo-left-shift by 3 words.
// Similar logic applies for elements 0 and 1.
foreach Idx = [ [0,2], [1,1], [3,3] ] in {
def : Pat<(store (i32 (extractelt v4i32:$A, !head(Idx))), xoaddr:$src),
(STIWX (EXTRACT_SUBREG (XXSLDWI $A, $A, !head(!tail(Idx))),
sub_64), xoaddr:$src)>;
def : Pat<(store (f32 (extractelt v4f32:$A, !head(Idx))), xoaddr:$src),
(STIWX (EXTRACT_SUBREG (XXSLDWI $A, $A, !head(!tail(Idx))),
sub_64), xoaddr:$src)>;
}
}
let Predicates = [HasP8Vector, IsLittleEndian, NoP9Vector] in {
def : Pat<(store (i64 (extractelt v2i64:$A, 0)), xoaddr:$src),
(XFSTOREf64 (EXTRACT_SUBREG (XXPERMDI $A, $A, 2), sub_64),
xoaddr:$src)>;
def : Pat<(store (f64 (extractelt v2f64:$A, 0)), xoaddr:$src),
(XFSTOREf64 (EXTRACT_SUBREG (XXPERMDI $A, $A, 2), sub_64),
xoaddr:$src)>;
def : Pat<(store (i64 (extractelt v2i64:$A, 1)), xoaddr:$src),
(XFSTOREf64 (EXTRACT_SUBREG $A, sub_64), xoaddr:$src)>;
def : Pat<(store (f64 (extractelt v2f64:$A, 1)), xoaddr:$src),
(XFSTOREf64 (EXTRACT_SUBREG $A, sub_64), xoaddr:$src)>;
}
let Predicates = [IsLittleEndian, HasVSX] in {
// Little endian, available on all targets with VSX
def : Pat<(v2f64 (build_vector f64:$A, f64:$B)),
(v2f64 (XXPERMDI
(COPY_TO_REGCLASS $B, VSRC),
(COPY_TO_REGCLASS $A, VSRC), 0))>;
def : Pat<(v4f32 (build_vector f32:$D, f32:$C, f32:$B, f32:$A)),
(VMRGEW MrgFP.AC, MrgFP.BD)>;
def : Pat<(v4f32 (build_vector DblToFlt.A0, DblToFlt.A1,
DblToFlt.B0, DblToFlt.B1)),
(v4f32 (VMRGEW MrgFP.BAhToFlt, MrgFP.BAlToFlt))>;
// Convert 4 doubles to a vector of ints.
def : Pat<(v4i32 (build_vector DblToInt.A, DblToInt.B,
DblToInt.C, DblToInt.D)),
(v4i32 (VMRGEW MrgWords.CVDBS, MrgWords.CVCAS))>;
def : Pat<(v4i32 (build_vector DblToUInt.A, DblToUInt.B,
DblToUInt.C, DblToUInt.D)),
(v4i32 (VMRGEW MrgWords.CVDBU, MrgWords.CVCAU))>;
def : Pat<(v4i32 (build_vector ExtDbl.A0S, ExtDbl.A1S,
ExtDbl.B0S, ExtDbl.B1S)),
(v4i32 (VMRGEW MrgWords.CVB1A1S, MrgWords.CVB0A0S))>;
def : Pat<(v4i32 (build_vector ExtDbl.A0U, ExtDbl.A1U,
ExtDbl.B0U, ExtDbl.B1U)),
(v4i32 (VMRGEW MrgWords.CVB1A1U, MrgWords.CVB0A0U))>;
}
let Predicates = [HasDirectMove] in {
// Endianness-neutral constant splat on P8 and newer targets. The reason
// for this pattern is that on targets with direct moves, we don't expand
// BUILD_VECTOR nodes for v4i32.
def : Pat<(v4i32 (build_vector immSExt5NonZero:$A, immSExt5NonZero:$A,
immSExt5NonZero:$A, immSExt5NonZero:$A)),
(v4i32 (VSPLTISW imm:$A))>;
}
let Predicates = [IsBigEndian, HasDirectMove, NoP9Vector] in {
// Big endian integer vectors using direct moves.
def : Pat<(v2i64 (build_vector i64:$A, i64:$B)),
(v2i64 (XXPERMDI
(COPY_TO_REGCLASS (MTVSRD $A), VSRC),
(COPY_TO_REGCLASS (MTVSRD $B), VSRC), 0))>;
def : Pat<(v4i32 (build_vector i32:$A, i32:$B, i32:$C, i32:$D)),
(XXPERMDI
(COPY_TO_REGCLASS
(MTVSRD (RLDIMI AnyExts.B, AnyExts.A, 32, 0)), VSRC),
(COPY_TO_REGCLASS
(MTVSRD (RLDIMI AnyExts.D, AnyExts.C, 32, 0)), VSRC), 0)>;
def : Pat<(v4i32 (build_vector i32:$A, i32:$A, i32:$A, i32:$A)),
(XXSPLTW (COPY_TO_REGCLASS (MTVSRWZ $A), VSRC), 1)>;
}
let Predicates = [IsLittleEndian, HasDirectMove, NoP9Vector] in {
// Little endian integer vectors using direct moves.
def : Pat<(v2i64 (build_vector i64:$A, i64:$B)),
(v2i64 (XXPERMDI
(COPY_TO_REGCLASS (MTVSRD $B), VSRC),
(COPY_TO_REGCLASS (MTVSRD $A), VSRC), 0))>;
def : Pat<(v4i32 (build_vector i32:$A, i32:$B, i32:$C, i32:$D)),
(XXPERMDI
(COPY_TO_REGCLASS
(MTVSRD (RLDIMI AnyExts.C, AnyExts.D, 32, 0)), VSRC),
(COPY_TO_REGCLASS
(MTVSRD (RLDIMI AnyExts.A, AnyExts.B, 32, 0)), VSRC), 0)>;
def : Pat<(v4i32 (build_vector i32:$A, i32:$A, i32:$A, i32:$A)),
(XXSPLTW (COPY_TO_REGCLASS (MTVSRWZ $A), VSRC), 1)>;
}
let Predicates = [HasP8Vector] in {
def : Pat<(v1i128 (bitconvert (v16i8 immAllOnesV))),
(v1i128 (COPY_TO_REGCLASS(XXLEQVOnes), VSRC))>;
def : Pat<(v2i64 (bitconvert (v16i8 immAllOnesV))),
(v2i64 (COPY_TO_REGCLASS(XXLEQVOnes), VSRC))>;
def : Pat<(v8i16 (bitconvert (v16i8 immAllOnesV))),
(v8i16 (COPY_TO_REGCLASS(XXLEQVOnes), VSRC))>;
def : Pat<(v16i8 (bitconvert (v16i8 immAllOnesV))),
(v16i8 (COPY_TO_REGCLASS(XXLEQVOnes), VSRC))>;
}
let Predicates = [HasP9Vector] in {
// Endianness-neutral patterns for const splats with ISA 3.0 instructions.
def : Pat<(v4i32 (scalar_to_vector i32:$A)),
(v4i32 (MTVSRWS $A))>;
def : Pat<(v4i32 (build_vector i32:$A, i32:$A, i32:$A, i32:$A)),
(v4i32 (MTVSRWS $A))>;
def : Pat<(v16i8 (build_vector immNonAllOneAnyExt8:$A, immNonAllOneAnyExt8:$A,
immNonAllOneAnyExt8:$A, immNonAllOneAnyExt8:$A,
immNonAllOneAnyExt8:$A, immNonAllOneAnyExt8:$A,
immNonAllOneAnyExt8:$A, immNonAllOneAnyExt8:$A,
immNonAllOneAnyExt8:$A, immNonAllOneAnyExt8:$A,
immNonAllOneAnyExt8:$A, immNonAllOneAnyExt8:$A,
immNonAllOneAnyExt8:$A, immNonAllOneAnyExt8:$A,
immNonAllOneAnyExt8:$A, immNonAllOneAnyExt8:$A)),
(v16i8 (COPY_TO_REGCLASS (XXSPLTIB imm:$A), VSRC))>;
def : Pat<(v4i32 (scalar_to_vector FltToIntLoad.A)),
(v4i32 (XVCVSPSXWS (LXVWSX xoaddr:$A)))>;
def : Pat<(v4i32 (scalar_to_vector FltToUIntLoad.A)),
(v4i32 (XVCVSPUXWS (LXVWSX xoaddr:$A)))>;
def : Pat<(v4i32 (scalar_to_vector DblToIntLoadP9.A)),
(v4i32 (XXSPLTW (COPY_TO_REGCLASS
(XSCVDPSXWS (DFLOADf64 iaddrX4:$A)), VSRC), 1))>;
def : Pat<(v4i32 (scalar_to_vector DblToUIntLoadP9.A)),
(v4i32 (XXSPLTW (COPY_TO_REGCLASS
(XSCVDPUXWS (DFLOADf64 iaddrX4:$A)), VSRC), 1))>;
def : Pat<(v2i64 (scalar_to_vector FltToLongLoadP9.A)),
(v2i64 (XXPERMDIs (XSCVDPSXDS (COPY_TO_REGCLASS
(DFLOADf32 iaddrX4:$A),
VSFRC)), 0))>;
def : Pat<(v2i64 (scalar_to_vector FltToULongLoadP9.A)),
(v2i64 (XXPERMDIs (XSCVDPUXDS (COPY_TO_REGCLASS
(DFLOADf32 iaddrX4:$A),
VSFRC)), 0))>;
def : Pat<(v4f32 (PPCldsplat xoaddr:$A)),
(v4f32 (LXVWSX xoaddr:$A))>;
def : Pat<(v4i32 (PPCldsplat xoaddr:$A)),
(v4i32 (LXVWSX xoaddr:$A))>;
}
let Predicates = [IsISA3_0, HasDirectMove, IsBigEndian] in {
def : Pat<(i64 (extractelt v2i64:$A, 1)),
(i64 (MFVSRLD $A))>;
// Better way to build integer vectors if we have MTVSRDD. Big endian.
def : Pat<(v2i64 (build_vector i64:$rB, i64:$rA)),
(v2i64 (MTVSRDD $rB, $rA))>;
def : Pat<(v4i32 (build_vector i32:$A, i32:$B, i32:$C, i32:$D)),
(MTVSRDD
(RLDIMI AnyExts.B, AnyExts.A, 32, 0),
(RLDIMI AnyExts.D, AnyExts.C, 32, 0))>;
}
let Predicates = [IsISA3_0, HasDirectMove, IsLittleEndian] in {
def : Pat<(i64 (extractelt v2i64:$A, 0)),
(i64 (MFVSRLD $A))>;
// Better way to build integer vectors if we have MTVSRDD. Little endian.
def : Pat<(v2i64 (build_vector i64:$rA, i64:$rB)),
(v2i64 (MTVSRDD $rB, $rA))>;
def : Pat<(v4i32 (build_vector i32:$A, i32:$B, i32:$C, i32:$D)),
(MTVSRDD
(RLDIMI AnyExts.C, AnyExts.D, 32, 0),
(RLDIMI AnyExts.A, AnyExts.B, 32, 0))>;
}
// P9 Altivec instructions that can be used to build vectors.
// Adding them to PPCInstrVSX.td rather than PPCAltivecVSX.td to compete
// with complexities of existing build vector patterns in this file.
let Predicates = [HasP9Altivec, IsLittleEndian] in {
def : Pat<(v2i64 (build_vector WordToDWord.LE_A0, WordToDWord.LE_A1)),
(v2i64 (VEXTSW2D $A))>;
def : Pat<(v2i64 (build_vector HWordToDWord.LE_A0, HWordToDWord.LE_A1)),
(v2i64 (VEXTSH2D $A))>;
def : Pat<(v4i32 (build_vector HWordToWord.LE_A0, HWordToWord.LE_A1,
HWordToWord.LE_A2, HWordToWord.LE_A3)),
(v4i32 (VEXTSH2W $A))>;
def : Pat<(v4i32 (build_vector ByteToWord.LE_A0, ByteToWord.LE_A1,
ByteToWord.LE_A2, ByteToWord.LE_A3)),
(v4i32 (VEXTSB2W $A))>;
def : Pat<(v2i64 (build_vector ByteToDWord.LE_A0, ByteToDWord.LE_A1)),
(v2i64 (VEXTSB2D $A))>;
}
let Predicates = [HasP9Altivec, IsBigEndian] in {
def : Pat<(v2i64 (build_vector WordToDWord.BE_A0, WordToDWord.BE_A1)),
(v2i64 (VEXTSW2D $A))>;
def : Pat<(v2i64 (build_vector HWordToDWord.BE_A0, HWordToDWord.BE_A1)),
(v2i64 (VEXTSH2D $A))>;
def : Pat<(v4i32 (build_vector HWordToWord.BE_A0, HWordToWord.BE_A1,
HWordToWord.BE_A2, HWordToWord.BE_A3)),
(v4i32 (VEXTSH2W $A))>;
def : Pat<(v4i32 (build_vector ByteToWord.BE_A0, ByteToWord.BE_A1,
ByteToWord.BE_A2, ByteToWord.BE_A3)),
(v4i32 (VEXTSB2W $A))>;
def : Pat<(v2i64 (build_vector ByteToDWord.BE_A0, ByteToDWord.BE_A1)),
(v2i64 (VEXTSB2D $A))>;
}
let Predicates = [HasP9Altivec] in {
def: Pat<(v2i64 (PPCSExtVElems v16i8:$A)),
(v2i64 (VEXTSB2D $A))>;
def: Pat<(v2i64 (PPCSExtVElems v8i16:$A)),
(v2i64 (VEXTSH2D $A))>;
def: Pat<(v2i64 (PPCSExtVElems v4i32:$A)),
(v2i64 (VEXTSW2D $A))>;
def: Pat<(v4i32 (PPCSExtVElems v16i8:$A)),
(v4i32 (VEXTSB2W $A))>;
def: Pat<(v4i32 (PPCSExtVElems v8i16:$A)),
(v4i32 (VEXTSH2W $A))>;
}
}
// Put this P9Altivec related definition here since it's possible to be
// selected to VSX instruction xvnegsp, avoid possible undef.
let Predicates = [HasP9Altivec] in {
def : Pat<(v4i32 (PPCvabsd v4i32:$A, v4i32:$B, (i32 0))),
(v4i32 (VABSDUW $A, $B))>;
def : Pat<(v8i16 (PPCvabsd v8i16:$A, v8i16:$B, (i32 0))),
(v8i16 (VABSDUH $A, $B))>;
def : Pat<(v16i8 (PPCvabsd v16i8:$A, v16i8:$B, (i32 0))),
(v16i8 (VABSDUB $A, $B))>;
// As PPCVABSD description, the last operand indicates whether do the
// sign bit flip.
def : Pat<(v4i32 (PPCvabsd v4i32:$A, v4i32:$B, (i32 1))),
(v4i32 (VABSDUW (XVNEGSP $A), (XVNEGSP $B)))>;
}
|